DESCRIPTION
SIGNAL PROCESSING APPARATUS AND METHOD, SIGNAL PROCESSING
SYSTEM, AND PROGRAM
5 TECHNICAL FIELD
[OOOl]
The present technique relates to signal processing
apparatuses and methods, signal processing systems, and
programs, and more particularly, to a signal processing
10 apparatus and method, a signal processing system, and a
program that are designed to appropriately add a
harmonizing voice when a person sings with an
accompaniment played by a karaoke machine or the like.
15 BACKGROUND ART
[0002]
Karaoke machines are widely used these days, and
there are a wide variety of them ranging from online
karaoke machines installed in karaoke bars to simple
20 karaoke functions to be executed by mobile devices. A
karaoke machine is an apparatus that reproduces recorded
accompaniment music instead of providing live music, and
allows a person to sing with an accompaniment or play a
melody line (a main theme) on an instrument along with an
25 accompaniment. Also, such an act may sometimes be
referred to as karaoke.
[0003]
It is known that a conventional karaoke machine has
a function (hereinafter referred to as a harmonizing
30 function) to add a sound (hereinafter referred to as a
harmonizing sound) consonant with a singing voice
(hereinafter referred to as a vocalized sound) of a user
to the vocalized sound (see Patent Document 1). This
function generates a harmonizing sound formed with a
sound that is above or below a vocalized sound input
5 through a microphone by a certain interval (the third in
a musical scale, for example), and adds the harmonizing
sound to the original vocalized sound. In this manner,
the harmonizing function is realized. Other than this
method, there are a number of methods developed for
10 creating more beautiful harmonies.
CITATION LIST
PATENT DOCUMENT
[0004]
Patent Document 1: JP 8-50493 A
SUMMARY OF THE INVENTION
PROBLEMS TO BE SOLVED BY THE INVENTION
[0005]
20 However, harmonizing sound adding periods are not
automatically set, and need to be set manually. In a
case where a performer needs to determine whether to
enable or disable the harmonizing function each time, for
example, the performer has to determine the time to do so
25 while singing with an accompaniment played by a karaoke
machine. Therefore, there is a possibility that the
performer cannot really enjoy singing with an
accompaniment played by the karaoke machine.
[0006]
30 In a case where harmonizing sound adding periods
are set for each tune beforehand by a karaoke music
distributor, the work to set the harmonizing sound adding
periods leads to higher costs. Furthermore, if a
harmonizing sound is added to an entire tune from the top
to the bottom, the performer might find singing the tune
5 monotonous and boring.
[0007]
The present technique has been developed in view of
those circumstances, and an object thereof is to provide
a karaoke machine that can output a wide variety of
10 enjoyable accompaniments by appropriately controlling
harmonizing sound adding periods in accordance with each
tune and the way of singing of each performer, cut the
cost of setting harmonizing sound adding periods in
advance, and save each performer from the trouble of
15 operating the harmonizing function.
SOLUTIONS TO PROBLEMS
[0008]
A signal processing apparatus of one aspect of the
20 present technique includes: a singing enthusiasm
calculating unit that calculates a degree of singing
enthusiasm formed with a feature quantity indicating the
status of singing enthusiasm of a performer of a tune; a
harmonizing voice signal superimposition determining unit
25 that determines whether to superimpose a harmonizing
voice signal on a singing voice signal of the performer
of the tune based on the degree of singing enthusiasm
calculated by the singing enthusiasm calculating unit;
and a harmonizing voice signal superimposing unit that
30 superimposes the harmonizing voice signal on the singing
voice signal based on a result of the determination
performed by the harmonizing voice signal superimposition
determining unit.
[0009]
The singing enthusiasm calculating unit may be
5 designed to calculate the degree of singing enthusiasm
formed with the feature quantity indicating the status of
singing enthusiasm of the performer based on a singing
voice signal of the performer of the tune.
[OOlO]
10 The signal processing apparatus may further include
a biological information acquiring unit that acquires
biological information about the performer. The singing
enthusiasm calculating unit may be designed to calculate
the degree of singing enthusiasm formed with the feature
15 quantity indicating the status of singing enthusiasm of
the performer based on the biological information about
the performer of the tune.
[ OOll]
The harmonizing voice signal superimposition
20 determining unit may be designed to determine whether to
superimpose the harmonizing voice signal on the singing
voice signal of the performer of the tune by comparing
the degree of singing enthusiasm calculated by the
singing enthusiasm calculating unit with a singing
25 enthusiasm threshold value that is set with respect to
the degree of singing enthusiasm, and determine that the
harmonizing voice signal is to be superimposed on the
singing voice signal of the performer of the tune when
the degree of singing enthusiasm is higher than the
30 singing enthusiasm threshold value.
[0012]
The signal processing apparatus may further include
an excitement calculating unit that calculates a degree
of excitement of the tune based on a music audio signal
that is the audio signal of the tune. The harmonizing
5 voice signal superimposition determining unit may be
designed to determine whether to superimpose the
harmonizing voice signal on the singing voice signal
based on the degree of singing enthusiasm calculated by
the singing enthusiasm calculating unit and the degree of
10 excitement calculated by the excitement calculating unit.
[0013]
The singing enthusiasm threshold calculating unit
may be designed to calculate a singing enthusiasm
threshold value by using the average value of the degrees
15 of singing enthusiasm of performers. The harmonizing
voice signal superimposition determining unit may be
designed to determine whether to superimpose the
harmonizing voice signal on the singing voice signal of
the performer of the tune by comparing the degree of
20 singing enthusiasm calculated by the singing enthusiasm
calculating unit with the singing enthusiasm threshold
value that is set with respect to the degree of singing
enthusiasm and is determined by using the average value
of the degrees of singing enthusiasm of the performers,
25 and determine that the harmonizing voice signal is to be
superimposed on the singing voice signal of the performer
of the tune when the degree of singing enthusiasm is
higher than the singing enthusiasm threshold value.
[0014]
30 A signal processing system of the present technique
includes: an information processing apparatus that
includes: a singing enthusiasm acquiring unit that
acquires degrees of singing enthusiasm calculated by
singing enthusiasm calculating units from signal
processing apparatuses of any of claims 1 through 6 via a
5 network, the signal processing apparatuses including the
respective singing enthusiasm calculating units that
calculate the degrees of singing enthusiasm; a singing
enthusiasm threshold calculating unit that calculates a
singing enthusiasm threshold value by using the average
10 value of the degrees of singing enthusiasm obtained by
the singing enthusiasm acquiring unit from the signal
processing apparatuses; and a delivering unit that
delivers the singing enthusiasm threshold value
calculated by the singing enthusiasm threshold
15 calculating unit to the signal processing apparatuses;
and the signal processing apparatus of any of claims 1
through 6. The harmonizing voice signal superimposition
determining unit may be designed to determine whether to
superimpose the harmonizing voice signal on the singing
20 voice signal of the performer of the tune by comparing
the degree of singing enthusiasm calculated by the
singing enthusiasm calculating unit with the singing
enthusiasm threshold value that is set with respect to
the degree of singing enthusiasm and is delivered from
25 the delivering unit, and determine that the harmonizing
voice signal is to be superimposed on the singing voice
signal of the performer of the tune when the degree of
singing enthusiasm is higher than the singing enthusiasm
threshold value.
30 [0015]
A signal processing method of one aspect of the
present technique includes: a singing enthusiasm
calculating step of calculating a degree of singing
enthusiasm formed with a feature quantity indicating the
status of singing enthusiasm of a performer of a tune,
5 the singing enthusiasm calculating step being carried out
at a singing enthusiasm calculating unit that calculates
the degree of singing enthusiasm formed with the feature
quantity indicating the status of singing enthusiasm of
the performer of the tune; a harmonizing voice signal
10 superimposition determining step of determining whether
to superimpose a harmonizing voice signal on a singing
voice signal of the performer of the tune based on the
degree of singing enthusiasm calculated by the processing
in the singing enthusiasm calculating step, the
15 harmonizing voice signal superimposition determining step
being carried out at a harmonizing voice signal
superimposition determining unit that determines whether
to superimpose the harmonizing voice signal on the
singing voice signal of the performer of the tune based
20 on the degree of singing enthusiasm calculated by the
singing enthusiasm calculating unit; and a harmonizing
voice signal superimposing step of superimposing the
harmonizing voice signal on the singing voice signal
based on a result of the determination performed by the
25 processing in the harmonizing voice signal
superimposition determining step, the harmonizing voice
signal superimposing step being carried out at a
harmonizing voice signal superimposing unit that
superimposes the harmonizing voice signal on the singing
30 voice signal based on a result of the determination
performed by the harmonizing voice signal superimposition
determining unit.
[0016]
A program of one aspect of the present technique
causes a computer to perform an operation that includes:
5 a singing enthusiasm calculating step of calculating a
degree of singing enthusiasm formed with a feature
quantity indicating the status of singing enthusiasm of a
performer of a tune, the singing enthusiasm calculating
step being carried out at a singing enthusiasm
10 calculating unit; a harmonizing voice signal
superimposition determining step of determining whether
to superimpose a harmonizing voice signal on a singing
voice signal of the performer of the tune based on the
degree of singing enthusiasm calculated by the processing
15 in the singing enthusiasm calculating step, the
harmonizing voice signal superimposition determining step
being carried out at a harmonizing voice signal
superimposition determining unit; and a harmonizing voice
signal superimposing step of superimposing the
20 harmonizing voice signal on the singing voice signal
based on a result of the determination performed by the
processing in the harmonizing voice signal
superimposition determining step, the harmonizing voice
signal superimposing step being carried out at a
25 harmonizing voice signal superimposing unit, the computer
controlling a signal processing apparatus that includes:
the singing enthusiasm calculating unit that calculates
the degree of singing enthusiasm formed with the feature
quantity indicating the status of singing enthusiasm of
30 the performer of the tune; the harmonizing voice signal
superimposition determining unit that determines whether
to superimpose the harmonizing voice signal on the
singing voice signal of the performer of the tune based
on the degree of singing enthusiasm calculated by the
singing enthusiasm calculating unit; and the harmonizing
5 voice signal superimposing unit that superimposes the
harmonizing voice signal on the singing voice signal
based on a result of the determination performed by the
harmonizing voice signal superimposition determining unit.
[0017]
10 In one aspect of the present technique, a degree of
singing enthusiasm formed with a feature quantity
indicating the status of singing enthusiasm of a
performer of a tune is calculated, a check is made to
determine whether to superimpose a harmonizing voice
15 signal on a singing voice signal of the performer of the
tune based on the calculated degree of singing enthusiasm,
and the harmonizing voice signal is superimposed on the
singing voice signal based on a result of the
determination.
20 [0018]
A signal processing apparatus of the present
technique may be an independent apparatus, or may be a
block that performs signal processing.
25 EFFECTS OF THE INVENTION
[0019]
According to the present technique, appropriate
harmonizing sound adding periods can be set in accordance
with each tune and the way of singing of each performer.
BRIEF DESCRIPTION OF DRAWINGS
[0020]
Fig. 1 is a diagram showing an example structure of
an embodiment of a signal processing system in which
signal processing apparatuses of the present technique
5 are used.
Fig. 2 is a diagram for explaining an example
structure of a voice processing apparatus.
Fig. 3 is a diagram for explaining an example
structure of the DSP.
10 Fig. 4 is a diagram for explaining an example
structure of the harmonizing signal controlling unit.
Fig. 5 is a diagram for explaining an example
structure of the singing enthusiasm server.
Fig. 6 is a flowchart for explaining a playing
15 process.
Fig. 7 is a flowchart for explaining a harmony
control process.
Fig. 8 is a flowchart for explaining a singing
enthusiasm calculation process.
20 Fig. 9 is a flowchart for explaining a musical
excitement calculation process.
Fig. 10 is a diagram for explaining a calculation
of a degree of singing enthusiasm.
Fig. 11 is a diagram for explaining an example
25 structure of a general-purpose personal computer.
MODES FOR CARRYING OUT THE INVENTION
[0021]
[Example Structure of a Signal Processing System to
30 Which the Present Technique Is Applied]
Referring to Fig. 1, an example structure of a
signal processing system to which the present technique
is applied is described.
[0022]
The signal processing system shown in Fig. 1
5 includes voice processing apparatuses 1-1 through 1-n
each formed with a karaoke machine that can perform
communication via a so-called network 4 and is installed
in a karaoke bar, a singing enthusiasm server 2, and a
music database 3. It should be noted that the voice
10 processing apparatuses 1-1 through 1-n will be
hereinafter referred to simply as the voice processing
apparatuses 1 as long as there is no particular need to
distinguish those apparatuses from one another. The same
applies to the other structures.
15 [0023]
Each voice processing apparatus 1 is a karaoke
machine that is installed in a so-called karaoke bar or
the like, and, when an operation instruction is issued
from a performer (not shown), downloads and plays the
20 audio data of the designated tune from the music database
3 via the network 4 such as the Internet. Based on a
singing voice signal generated from the performer singing,
the voice processing apparatus 1 calculates a degree of
singing enthusiasm, adds (superimposes) a harmonizing
25 voice (a harmonizing sound) to (on) the singing voice
signal (a vocal sound) in accordance with the calculated
degree of singing enthusiasm, outputs the singing voice
signal having the harmonizing voice added thereto, and
supplies information about the calculated degree of
30 singing enthusiasm to the singing enthusiasm server 2 via
the network 4. Having obtained information about degrees
of singing enthusiasm supplied from the voice processing
apparatuses 1 via the network 4, the singing enthusiasm
server 2 calculates the average degree of singing
enthusiasm of each tune, and stores a singing enthusiasm
5 threshold value that is such an offset value as to lower
the average value by a predetermined value. The singing
enthusiasm server 2 delivers the stored information about
the singing enthusiasm threshold value to a voice
processing apparatus 1 via the network 4 when the voice
10 processing apparatus 1 downloads the audio data of the
tune from the music database 3. Based on a comparison
between the degree of singing enthusiasm determined from
the singing voice signal of the performer and the singing
enthusiasm threshold value obtained via the network 4,
15 the voice processing apparatus 1 determines intervals at
which a harmonizing voice is to be added, and
superimposes the harmonizing voice on the singing voice
signal. The music database 3 accumulates designated
music data. Hereinafter, the action to superimpose a
20 harmonizing voice that is a consonant sound on a singing
voice signal will be referred to as "harmonizing",
"adding a harmonizing voice", or "switching on the
harmonizing function".
[0024]
25 [Example Structure of a Voice Processing Apparatus]
Referring now to Fig. 2, an example structure of a
voice processing apparatus 1 is described.
[0025]
The voice processing apparatus 1 includes a CPU
30 (Central Processing Unit) 21, a RAM (Random Access
Memory) 22, a ROM (Read Only Memory) 23, a
transmission/reception unit 24, a storage unit 25, a
system bus 26, a remote controller light receiving unit
27, and a monitor 28. The voice processing apparatus 1
also includes a MIDI (Musical Instrument Digital
5 Interface) sound source unit 29, a DSP (Digital Signal
Processor) 30, a D/A ( Digital-Analog) converter 31, and
an amplifier 32. The voice processing apparatus 1
further includes a speaker 33, an A/D (Analog-Digital)
converter 34, an amplifier 35, and a microphone 36.
10 [0026]
The CPU 21 reads a predetermined program and data
that are stored beforehand in the ROM 23 or the storage
unit 25 formed with an HDD (Hard Disk Drive) or an SSD
(Solid State Drive) via the system bus 26, loads the
15 predetermined program and the data into the RAM 22, and
performs predetermined processes. The CPU 21 controls
the entire operation of the voice processing apparatus 1
by performing the series of processes.
[0027]
20 The transmission/reception unit 24 is a so-called
Ethernet (a registered trademark) board or the like that
downloads a tune from the music database 3 via the
network 4, and uploads information about a degree of
singing enthusiasm calculated by the DSP 30 based on a
25 singing voice signal of a performer to the singing
enthusiasm server 2.
[0028]
The storage unit 25 is formed with an HDD or an SSD
or the like that is controlled by the CPU 21. The
30 storage unit 25 stores data and programs necessary for
performing processing, and also stores downloaded music
data. The storage unit 25 supplies the downloaded music
data to the CPU 21, the MIDI sound source unit 29, and
the DSP 30 via the system bus 26.
[0029]
5 The remote controller light receiving unit 27
receives a signal generated as an infrared ray by the
remote controller 13 for operating the voice processing
apparatus 1, converts the signal into a predetermined
signal, and supplies the converted signal to the CPU 21
10 via the system bus 26.
[0030]
The monitor 28 is formed with an LCD (Liquid
Crystal Display), an organic EL (Electronic Luminescent),
or the like, is controlled by the CPU 21, and displays
15 various kinds of information and processing results.
[0031]
The MIDI sound source unit 29 converts music data
in the MIDI format downloaded by the
transmission/reception unit 24 from the music database 3
20 via the network 4 into a digital signal that can be
processed by the DSP 30, and outputs the digital signal
to the DSP 30.
[0032]
The microphone 36 is held by a performer, collects
25 a singing voice emitted from the performer, and supplies
the singing voice as an analog signal to the amplifier 35.
In the microphone 36, sensors 36a and 36b are provided at
portions to be touched by the performer to hold the main
body, the sensors 36a and 36b measure a pulse rate and a
30 body temperature of the performer, and supply the pulse
rate and the body temperature to the DSP 30. The
amplifier 35 amplifies the analog signal formed with the
singing voice signal supplied from the microphone 36 by a
predetermined amplification factor, and supplies the
amplified analog signal to the A/D converter 34. The A/D
5 converter 34 converts the singing voice signal formed
with the analog signal amplified by a predetermined
amplification factor by the amplifier 35 into a digital
signal that can be processed by the DSP 30, and supplies
the digital signal.
10 [0033]
The DSP 30 is controlled by the CPU 21 via the
system bus 26, adds a harmonizing voice and an echo
effect to a tune formed with the digital signal from the
MIDI sound source unit 29 and to the singing voice signal
15 formed with the digital signal supplied from the A/D
converter 34 through a predetermined process, and
outputs the resultant signal to the D/A converter 31.
The D/A converter 31 converts the voice signal formed
with the digital signal subjected to various kinds of
20 processes by the DSP 30 into an analog signal, and
supplies the analog signal to the amplifier 32. The
amplifier 32 amplifies the voice signal converted into
the analog signal by a predetermined amplification factor,
and outputs the resultant signal as a voice through the
25 speaker 33.
[0034]
[Example Structure of the DSP]
Referring now to Fig. 3, an example structure of
the DSP 30 is described.
30 [0035]
The DSP 30 includes a singing enthusiasm
calculating unit 51, a pitch detecting unit 52, a
harmonizing key determining unit 53, a pitch shifter 54,
a musical excitement calculating unit 55, a harmonizing
signal controlling unit 56, an echo effect adding unit 57,
5 and an adder 58.
[0036]
Based on the singing voice signal supplied from the
A/D converter 34 and the information about the pulse rate
and the body temperature of the performer supplied from
10 the microphone 36, the singing enthusiasm calculating
unit 51 chronologically calculates a degree of singing
enthusiasm, stores the degree of singing enthusiasm into
an internal storage unit 51a, and supplies the degree of
singing enthusiasm to the harmonizing signal controlling
15 unit 56. When the supply of music data is completed, and
the playing is ended, the singing enthusiasm calculating
unit 51 controls the transmission/reception unit 24 to
transmit the information about the degree of singing
enthusiasm stored chronologically in the storage unit 51a
20 and information identifying the music data to the singing
enthusiasm server 2.
[0037]
The pitch detecting unit 52 detects the pitch or
the fundamental frequency of the singing voice signal
25 supplied from the A/D converter 34, converts the
fundamental frequency into pitch notations (sol-fa names),
and supplies the pitch notations to the harmonizing key
determining unit 53. The harmonizing key determining
unit 53 acquires scale and chord information from music
30 data stored in the storage unit 25 via the system bus 26,
determines the key to harmonize with the current pitch
notation (a harmonizing key that is higher or lower by
the third or the fifth) based on the information, and
supplies the harmonizing key to the pitch shifter 54.
The pitch shifter 54 shifts the singing voice signal by
5 the degrees in accordance with the harmonizing key, to
generate and supply a harmonizing voice signal to the
harmonizing signal controlling unit 56.
[0038]
Based on music data supplied from the MIDI sound
10 source unit 29, the musical excitement calculating unit
55 calculates a degree of musical excitement, and
supplies the degree of musical excitement to the
harmonizing signal controlling unit 56.
[0039]
15 Based on the degree of singing enthusiasm supplied
from the singing enthusiasm calculating unit 51 and the
degree of musical excitement supplied from the musical
excitement calculating unit 55, the harmonizing signal
controlling unit 56 performs control to output the
20 singing voice signal as it is or to output the singing
voice signal having the harmonizing voice signal added
thereto. The structure of the harmonizing signal
controlling unit 56 will be described later in detail,
with reference to Fig. 4.
25 [0040]
The echo effect adding unit 57 adds an echo effect
to the singing voice signal output from the harmonizing
signal controlling unit 56 or to the singing voice signal
having the harmonizing voice signal added thereto, and
30 supplies the resultant signal to the adder 58.
[0041]
The adder 58 adds the audio signal of the tune
supplied from the MIDI sound source unit 29 to the
singing voice signal supplied from the echo effect adding
unit 57 or to the singing voice signal having the
5 harmonizing voice added thereto, and output the combined
signals.
[0042]
[Example Structure of the Harmonizing Signal
Controlling Unit]
10 Referring now to Fig. 4, an example structure of
the harmonizing signal controlling unit 56 is described.
[0043]
The harmonizing signal controlling unit 56 includes
a singing voice signal gain adjusting unit 71, a
15 harmonizing voice signal gain adjusting unit 72, an adder
73, a switch 74, a singing enthusiasm threshold
determining unit 75, an output sound selecting unit 76,
and a musical excitement threshold determining unit 77.
[0044]
20 The singing voice signal gain adjusting unit 71
adjusts the gain of the singing voice signal, and outputs
the resultant signal to the adder 73 and a terminal 74a
of the switch 74. The harmonizing voice signal gain
adjusting unit 72 adjusts the gain of the harmonizing
25 voice signal, and outputs the resultant signal to the
adder 73. The adder 73 adds and combines (superimposes)
the singing voice signal and the harmonizing voice signal
having the gains adjusted, and outputs the resultant
signal to a terminal 74b of the switch 74.
30 [0045]
The singing enthusiasm threshold determining unit
75 controls the transmission/reception unit 24 to obtain
a singing enthusiasm threshold value from the singing
enthusiasm server 2, compares the singing enthusiasm
threshold value with the degree of singing enthusiasm
5 supplied from the singing enthusiasm calculating unit 51,
and outputs the comparison result to the output sound
selecting unit 76. The musical excitement threshold
determining unit 77 compares a musical excitement
threshold value with the degree of musical excitement
10 supplied from the musical excitement calculating unit 55,
and supplies the comparison result to the output sound
selecting unit 76.
[0046]
Based on the respective comparison results supplied
15 from the singing enthusiasm threshold determining unit 75
and the musical excitement threshold determining unit 77,
the output sound selecting unit 76 controls the switch 74
to connect to the terminal 74a or the 74b. As a result,
the output sound selecting unit 76 controls the switch 74
20 to connect to the terminal 74a and outputs the singing
voice signal, or controls the switch 74 to connect to the
terminal 74b and outputs the singing voice signal
combined with the harmonizing voice signal (or having the
harmonizing voice signal superimposed thereon).
25 [0047]
[Example Structure of the Singing Enthusiasm
Server]
Referring now to Fig. 5, an example structure of
the singing enthusiasm server 2 is described.
30 COO481
The singing enthusiasm server 2 includes a CPU 91,
a RAM 92, a ROM 93, a transmission/reception unit 94, a
storage unit 95, a system bus 96, a singing enthusiasm
threshold generating unit 97, and a singing enthusiasm
threshold storage unit 98. The CPU 91 reads a
5 predetermined program and data that are stored beforehand
in the ROM 93 or the storage unit 95 formed with an HDD
or an SSD via the system bus 96, loads the predetermined
program and the data into the RAM 92, and performs
predetermined processes. The CPU 91 controls the entire
10 operation of the singing enthusiasm server 2 by
performing the series of processes.
[0049]
The transmission/reception unit 94 is a so-called
Ethernet (a registered trademark) board, obtains singing
15 enthusiasm information about each tune from the voice
processing apparatuses 1 that are karaoke machines via
the network 4, and stores the information into the
storage unit 95. The transmission/reception unit 94
reads the singing enthusiasm threshold value stored in
20 the singing enthusiasm threshold storage unit 98, and
delivers the singing enthusiasm threshold value to the
voice processing apparatuses 1.
[0050]
When new singing enthusiasm information associated
25 with a tune is stored into the storage unit 95, the
singing enthusiasm threshold generating unit 97
calculates the average value of the degree of singing
enthusiasm of the tune, and offsets the average degree of
singing enthusiasm by a predetermined value or a
30 predetermined proportion, to generate the singing
enthusiasm threshold value. The singing enthusiasm
threshold generating unit 97 then stores the information
about the generated singing enthusiasm threshold value
associated with the tune into the singing enthusiasm
threshold storage unit 98.
5 [0051]
[Playing Process]
Referring now to the flowchart in Fig. 6, a playing
process is described.
[0052]
10 In step S1, the CPU 21 determines whether a tune
has been designated by operating the remote controller 13
and a play instruction signal has been received by the
remote controller light receiving unit 27, and repeats
this procedure until determining that light has been
15 received. If a tune has been designed by a user
operating the remote controller 13, for example, and a
play instruction signal has been issued and been received
by the remote controller light receiving unit 27 in step
S1, the process moves on to step S2.
20 [0053]
In step 52, the CPU 21 controls the
transmission/reception unit 24 to download the designated
music data from the music database 3 via the network 4,
and stores the downloaded music data into the storage
25 unit 25.
[0054]
In step S3, the CPU 21 instructs the DSP 30 to
download the singing enthusiasm threshold value
corresponding to the downloaded tune from the singing
30 enthusiasm server 2 via the network 4. In response to
this instruction, the harmonizing signal controlling unit
56 of the DSP 30 controls the transmission/reception unit
24 via the system bus 26, and requests the singing
enthusiasm threshold value corresponding to the
downloaded music data from the singing enthusiasm server
5 2 via the network 4.
[0055]
In step S21, the CPU 91 of the singing enthusiasm
server 2 controls the transmission/reception unit 94, and
determines whether a request for the singing enthusiasm
10 threshold value has been issued, and repeats the same
procedure until such a request is made. If it is
determined in step S21 that the singing enthusiasm
threshold value has been requested by the processing in
step S3, the process moves on to step S22.
15 [0056]
In step ,522, the CPU 91 reads the information about
the singing enthusiasm threshold value corresponding to
the music data downloaded by a voice processing apparatus
1 among the singing enthusiasm threshold value
20 information stored in the singing enthusiasm threshold
storage unit 98. The CPU 91 then controls the
transmission/reception unit 94 to transmit the read
information about the singing enthusiasm threshold value
to the voice processing apparatus 1 that has made the
25 request via the network 4.
[0057]
In step S4, the DSP 30 controls the
transmission/reception unit 24 to obtain the singing
enthusiasm threshold value information transmitted from
30 the singing enthusiasm server 2, and stores the
information into the singing enthusiasm threshold
determining unit 75.
LO0581
In step S5, the MIDI sound source unit 29 reads the
music data in the MIDI format stored in the storage unit
5 25, converts the music data into a digital audio signal
that can be reproduced by the DSP 30, and supplies the
digital audio signal. Based on the digital audio signal
supplied sequentially from the MIDI sound source unit 29,
the DSP 30 reproduces the audio signal of the tune, and
10 causes the D/A converter 31 to convert the audio signal
into an analog signal. The amplifier 32 amplifies the
analog signal by a predetermined amplification factor,
and the amplified analog signal is output through the
speaker 33, to start the playing. In response to that,
15 the performer starts singing with the accompaniment music
output through the speaker 33 while holding the
microphone 36. The sensors 36a and 36b of the microphone
36 measure the pulse rate of the performer and the body
temperature of the performer, respectively, and supplies
20 the biological information to the DSP 30.
[0059]
In step S6, the DSP 30 performs a harmony control
process based on the singing voice signal of the
performer that is input through the microphone 36, adds
25 (superimposes) a harmonizing voice signal to (on) the
singing voice signal if necessary, and outputs the voice
through the speaker 33.
[0060]
In step S7, the DSP 30 determines whether the
30 playing has been ended or whether the supply of the music
data from the MIDI sound source unit 29 has been stopped.
If the playing has not been ended yet, the process
returns to step S6. Specifically, the DSP 30 continues
to perform the harmony control process until the playing
is ended, and repeats the step of adding a harmonizing
5 voice signal to the singing voice signal if necessary.
At this point, the DSP 30 continues to chronologically
calculate a degree of singing enthusiasm and a degree of
musical excitement, and stores the result of the singing
enthusiasm calculation. It should be noted that the
10 harmony control process will be described later in detail,
with reference to the flowchart in Fig. 7.
[0061]
If it is determined in step S7 that the playing has
been ended, for example, the process moves on to step S8.
15 [0062]
In step S8, the singing enthusiasm calculating unit
51 of the DSP 30 controls the transmission/reception unit
24 to upload the singing enthusiasm information stored
chronologically in the storage unit 51a, together with
20 the information identifying the music data and the
information indicating the end of play, to the singing
enthusiasm server 2.
[0063]
Meanwhile, in the singing enthusiasm server 2,
25 after the singing enthusiasm threshold information is
transmitted by the processing in step S22, the singing
enthusiasm threshold generating unit 97 in step S23
controls the transmission/reception unit 94 and
determines whether the information indicating the end of
30 play has been transmitted from the voice processing
apparatus 1. In step S23, the same procedure is repeated
until it is determined that the information indicating
the end of play has been transmitted. If it is
determined in step S23 that the information indicating
the end of play has been transmitted by the processing in
5 step S8, for example, the process moves on to step S24.
[0064]
In step S24, the singing enthusiasm threshold
generating unit 97 controls the transmission/reception
unit 94 to obtain the information identifying the tune
10 and the singing enthusiasm information about the tune
transmitted together with the information indicating the
end of play, and stores the information into the storage
unit 95.
[0065]
15 In step S25, the singing enthusiasm threshold
generating unit 97 reads the singing enthusiasm
information corresponding to the obtained tune among the
singing enthusiasm information stored in the storage unit
95, processes the information statistically, and
20 calculates the singing enthusiasm threshold value. More
specifically, the singing enthusiasm threshold generating
unit 97 calculates the average degree of singing
enthusiasm corresponding to the obtained tune among the
singing enthusiasm information stored in the storage unit
25 95, and calculates the singing enthusiasm threshold value
that is the chronological information generated by
reducing the average value by an offset value.
[0066]
In step S26, the singing enthusiasm threshold
30 generating unit 97 rewrites and updates the information
stored in the singing enthusiasm threshold storage unit
98 with the calculated singing enthusiasm threshold value,
and saves (stores) the updated information.
[0067]
In the above described process, when a tune is
5 designated and a play start instruction is issued in the
voice processing apparatus 1, the singing enthusiasm
threshold information is downloaded from the singing
enthusiasm server 2, the music data is downloaded from
the music database 3, and the playing is started. In the
10 voice processing apparatus 1, a harmony control process
is performed based on the singing enthusiasm threshold
information, and a harmonizing voice signal is added to
the singing voice signal of the performer if necessary
while the tune is played. When the playing is ended, the
15 information about the degree of singing enthusiasm
chronologically calculated based on the singing voice
signal of the performer is uploaded to the singing
enthusiasm server 2, and the singing enthusiasm threshold
value is statistically calculated and updated each time.
20 [0068]
[Harmony Control Process]
Referring now to the flowchart in Fig. 7, the
harmony control process is described.
[0069]
25 In step S41, the pitch detecting unit 52 of the DSP
30 detects pitch that is the fundamental frequency of the
singing voice signal of the performer based on the
performer's singing voice signal input from the
microphone 36 via the amplifier 35 and the A/D converter
30 34. The pitch detecting unit 52 further converts the
detected pitch into pitch notations that are sol-fa names,
and supplies the information about the pitch notations to
the harmonizing key determining unit 53.
[0070]
In step S42, the harmonizing key determining unit
5 53 acquires scale and chord information from music data
stored in the storage unit 25 via the system bus 26, and
determines the key to harmonize with the current pitch
notation (a harmonizing key) based on the information.
The harmonizing key determining unit 53 supplies the
10 information about the determined harmonizing key to the
pitch shifter 54.
[0071]
In step S43, the pitch shifter 54 shifts the
fundamental frequency of the singing voice signal based
15 on the harmonizing key information supplied from the
harmonizing key determining unit 53, to generate and
supply the harmonizing voice signal to the harmonizing
signal controlling unit 56.
[0072]
20 In step S44, the singing enthusiasm calculating
unit 51 performs a singing enthusiasm calculation process
based on the singing voice signal and the pulse rate and
body temperature information supplied from the microphone
36, chronologically calculates a degree of singing
25 enthusiasm, and sequentially stores the degree of singing
enthusiasm into the storage unit 51a.
[0073]
[Singing Enthusiasm Calculation Process]
Referring now to the flowchart in Fig. 8, the
30 singing enthusiasm calculation process is described.
[0074]
In step S71, the singing enthusiasm calculating
unit 51 calculates the RMS (Root Mean Square) of the
singing voice signal at predetermined time intervals.
[0075]
5 In step S72, the singing enthusiasm calculating
unit 51 calculates the mean value of the fundamental
frequency of the singing voice signal or a mean pitch
value at predetermined time intervals.
[0076]
10 In step S73, the singing enthusiasm calculating
unit 51 calculates the reciprocal of the standard
deviation of the fundamental frequency of the singing
voice signal as the stability of the singing voice signal
or a degree of pitch stability at predetermined time
15 intervals.
100771
In step S74, the singing enthusiasm calculating
unit 51 acquires the information about the performer's
pulse rate measured by the sensor 36a of the microphone
20 36.
LO0781
In step S75, the singing enthusiasm calculating
unit 51 acquires the information about the performer's
body temperature measured by the sensor 36b of the
25 microphone 36.
[0079]
In step S76, the singing enthusiasm calculating
unit 51 calculates a degree of singing enthusiasm
according to the following equation (I), stores the
30 calculated degree of singing enthusiasm into the storage
unit 51a, and supplies the calculated degree of singing
enthusiasm to the harmonizing signal controlling unit 56.
[0080]
HS = a x RMS + P x mean pitch value + y x pitch
stability + 6 x pulse rate + E x body temperature (1)
5 [0081]
Here, HS represents the degree of singing
enthusiasm, RMS represents the root mean square of the
singing voice signal, and a, P, y, 6, and E represent the
weight coefficients of the respective parameters.
10 [0082]
That is, the degree of singing enthusiasm becomes
higher, as the respective parameters, which are the sound
pressure level represented by the root mean square of the
singing voice signal, the mean pitch value as the mean
15 value of the fundamental frequency, the degree of pitch
stability as the stability of the fundamental frequency,
the pulse rate, and the body temperature, become higher.
The degree of singing enthusiasm defined by the equation
(1) is merely an example, and may be defined in a
20 different manner. For example, in a case where the
microphone 36 is a conventional microphone that does not
have the sensors 36a and 36b, biological information such
as the pulse rate and the body temperature of the
performer may not be used as parameters. The biological
25 information may further include blood pressure or the
like. Furthermore, the weight coefficients a, P, y, 6,
and E may be arbitrarily set.
[0083]
Through the above process, a degree of singing
30 enthusiasm can be calculated based on the singing voice
signal of the performer and biological information about
the performer.
[0084]
Explanation now returns to the flowchart in Fig. 7.
[0085]
5 After the degree of singing enthusiasm is
calculated through the singing enthusiasm calculation
process in step S44, the musical excitement calculating
unit 55 in step S45 performs a musical excitement
calculation process, and calculates a degree of musical
10 excitement from the digital audio signal of the music
data supplied from the MIDI sound source unit 29.
[0086]
[Musical Excitement Calculation Process]
Referring now to the flowchart in Fig. 8, the
15 musical excitement calculation process is described.
[0087]
In step S91, the musical excitement calculating
unit 55 calculates the RMS of the singing voice signal at
predetermined time intervals, and cumulatively stores the
20 RMS.
[0088]
In step S92, the musical excitement calculating
unit 55 calculates the mean value of the past RMSs stored
prior to the calculations of the RMSs of the singing
25 voice signal at predetermined intervals in the latest
step.
[0089]
In step S93, the musical excitement calculating
unit 55 calculates a degree of musical excitement that is
30 the difference between the mean value of the RMSs
calculated in the latest step and the mean value of the
RMSs, and supplies the degree of musical excitement to
the harmonizing signal controlling unit 56.
[0090]
Through the above described process, the difference
5 between the mean value of the RMSs calculated at
predetermined time intervals and the mean value of the
past RMSs is set as the degree of musical excitement.
The degree of musical excitement is calculated not
necessarily by the above described technique, but may be
10 determined by detecting the so-called "hook-line", which
is the exciting part of a tune, and calculating a value
indicating the level of the hook-line.
[0091]
Explanation now returns to the flowchart in Fig. 7.
15 [0092]
After the degree of musical excitement is
calculated through the musical excitement calculation
process in step S45, the process moves on to step S46.
[0093]
20 In step S46, the harmonizing voice signal gain
adjusting unit 72 adjusts the gain of the harmonizing
voice signal supplied from the pitch shifter 54, and
supplies the resultant signal to the adder 73.
[0094]
25 In step S47, the singing voice signal gain
adjusting unit 71 adjusts the gain of the singing voice
signal supplied from the A/D converter 34, and supplies
the resultant signal to the adder 73 and the terminal 74a.
[0095]
30 In step S48, the singing enthusiasm threshold
determining unit 75 compares the degree of singing
enthusiasm supplied from the singing enthusiasm
calculating unit 51 with the singing enthusiasm threshold
value that has been downloaded from the singing
enthusiasm server 2 and been stored, and determines
5 whether the degree of singing enthusiasm is higher than
the singing enthusiasm threshold value. In a case where
the degree of singing enthusiasm is determined to be
higher than the singing enthusiasm threshold value in
step S48, for example, the singing enthusiasm threshold
10 determining unit 75 supplies the determination result to
the output sound selecting unit 76, and the process then
moves on to step S49.
[0096]
In step S49, the musical excitement threshold
15 determining unit 77 compares the degree of musical
excitement supplied from the musical excitement
calculating unit 55 with a predetermined musical
excitement threshold value, and determines whether the
degree of musical excitement is higher than the
20 predetermined musical excitement threshold value. In a
case where the degree of musical excitement is determined
to be higher than the predetermined musical excitement
threshold value in step S49, for example, the musical
excitement threshold determining unit 77 supplies the
25 determination result to the output sound selecting unit
76, and the process then moves on to step S50.
[ 0 0 97 ]
In step S50, the output sound selecting unit 76
connects the switch 74 to the terminal 74b based on the
30 determination results supplied from the singing
enthusiasm threshold determining unit 75 and the musical
excitement threshold determining unit 77. As a result,
the signal formed by combining the singing voice signal
and the harmonizing voice signal by the adder 73 is
supplied to the output sound selecting unit 76 via the
5 terminal 74b, and the output sound selecting unit 76 then
supplies the supplied combined signal generated by
combining the singing voice signal and the harmonizing
voice signal to the echo effect adding unit 57.
[0098]
10 In step S51, the echo effect adding unit 57 adds a
predetermined echo effect to the combined singing voice
signal generated by combining the singing voice signal
and the harmonizing voice signal, and outputs the
resultant signal to the adder 58.
15 [0099]
In step S52, the adder 58 combines the combined
singing voice signal having the echo effect added thereto
and the digital signal of the tune supplied from the MIDI
sound source unit 29, and outputs the resultant signal to
20 the D/A converter 31. Through this step, the combined
singing voice signal combined with the digital signal of
the tune is converted into an analog signal by the D/A
converter 31, is subjected to gain adjustment by the
amplifier 32, and is output through the speaker 33.
25 [OlOO]
In a case where the degree of singing enthusiasm is
determined to be lower than the singing enthusiasm
threshold value in step S48, on the other hand, the
singing enthusiasm threshold determining unit 75 supplies
30 the determination result to the output sound selecting
unit 76, and the process then moves on to step S53. Also,
in a case where the degree of musical excitement is
determined to be lower than the predetermined musical
excitement threshold value in step S49, the musical
excitement threshold determining unit 77 supplies the
5 determination result to the output sound selecting unit
76, and the process then moves on to step S53.
[ OlOl]
In step S53, the output sound selecting unit 76
connects the switch 74 to the terminal 74a based on the
10 determination results supplied from the singing
enthusiasm threshold determining unit 75 and the musical
excitement threshold determining unit 77. Only the
singing voice signal is then supplied to the output sound
selecting unit 76 via the terminal 74a, and the output
15 sound selecting unit 76 supplies only the supplied
singing voice signal to the echo effect adding unit 57.
[0102]
That is, in a case where the degree of singing
enthusiasm is higher than the singing enthusiasm
20 threshold value, and the degree of musical excitement is
higher than the musical excitement threshold value, the
singing voice signal is combined with the harmonizing
voice signal or the harmonizing function is switched on,
and the singing voice signal is output together with the
25 sound of the tune. In this manner, a harmonizing voice
is added to the singing voice signal of the performer in
accordance with the degree of singing enthusiasm that
varies with the way of singing of the performer and the
degree of musical excitement of the tune. Accordingly,
30 harmonizing periods can be appropriately set, and a
harmonizing voice or a consonant sound can be added. As
a result, the performer does not need to mind when to
switch on the harmonizing function, and the harmonizing
function can be appropriately switched on. Accordingly,
when using a karaoke machine, each performer can
5 concentrate on singing.
[0103]
As shown in Fig. 10, the singing enthusiasm
threshold value th is set at a value that is offset by a
predetermined level with respect to the average degree of
10 singing enthusiasm Ave of the same tune uploaded from a
voice processing apparatus 1 in the network 4, for
example. Although the degree of singing enthusiasm
varies with the way of singing of each performer, the
singing enthusiasm threshold value th is set at a value
15 that is offset for performers that cannot reach the
average degree of singing enthusiasm. Accordingly, a
larger number of performers can use the harmonizing
function when appropriate, even though the degree of
singing enthusiasm varies with the way of singing of each
20 performer. The singing enthusiasm threshold value th is
a value that is offset with respect to the average degree
of singing enthusiasm so as to facilitate switching on of
the harmonizing function, as described above. Therefore,
the offset value may be arbitrarily set, and may be zero
25 so as to set the average degree of singing enthusiasm as
the average degree of singing enthusiasm, for example.
[0104]
In the above described example, each voice
processing apparatus 1 uploads the information about a
30 degree of singing enthusiasm to the singing enthusiasm
server 2 via the network 4, and the singing enthusiasm
threshold value determined from the average value of the
degree of singing enthusiasm is downloaded and used. In
this manner, an appropriate singing enthusiasm threshold
value that reflects the intention of each performer with
5 higher precision can be set. However, after a degree of
singing enthusiasm that is close to the average is
calculated, the variation of the singing enthusiasm
threshold value is expected to become smaller. In view
of this, a singing enthusiasm threshold value may not be
10 downloaded from the singing enthusiasm server 2 each time.
Instead, a singing enthusiasm threshold value may be
downloaded and stored into each voice processing
apparatus 1, and be repeatedly used thereafter.
Alternatively, a singing enthusiasm threshold value may
15 be stored beforehand into each apparatus at the time of
shipment from the factory or the like, and be used
thereafter. Further, degrees of singing enthusiasm of
performers singing the same tune may be accumulated in
one voice processing apparatus 1 instead of being
20 transmitted via the network 4, and the singing enthusiasm
threshold value may be determined from the average value
of the degree of singing enthusiasm.
[0105]
Although the singing enthusiasm server 2 exists in
25 the network 4 in the above described example, the singing
enthusiasm server 2 may be replaced by information
processing apparatuses or servers that perform so-called
cloud computing. In that case, the cloud computing may
be performed only by the voice processing apparatuses 1
30 or karaoke machines.
[0106]
In the above described example, a singing voice of
each performer is used as a reference, and a consonant
sound or a harmonizing voice is superimposed on the
singing voice. However, a reference sound may not be a
5 singing voice, and may be a sound of a musical instrument
that is being played.
[0107]
As described above, according to the present
technique, a harmonizing sound or a so-called harmonizing
10 voice can be added to a singing voice when appropriate
for each tune or the singing manner of each performer in
each voice processing apparatus formed with a music
reproducing apparatus such as a so-called karaoke machine.
In that case, a performer does not need to pay attention
15 to harmonizing periods (timing), and accordingly, can
concentrate on singing. In addition to that, a
harmonizing voice can be added by the harmonizing
function. Thus, each performer can enjoy singing with
more comfort.
20 [0108]
The above described series of processes can be
performed by hardware, and can also be performed by
software. When the series of processes are to be
performed by software, the programs forming the software
25 are installed into a computer. Here, the computer may be
a computer incorporated into special-purpose hardware, or
may be a general-purpose personal computer that can
execute various kinds of functions as various kinds of
programs are installed thereinto.
30 [0109]
Fig. 11 is a block diagram showing an example
structure of the hardware of a computer that performs the
above described series of processes in accordance with
programs.
[OllO]
5 In the computer, a CPU (Central Processing Unit)
1001, a ROM (Read Only Memory) 1002, and a RAM (Random
Access Memory) 1003 are connected to one another by a bus
1004.
[Olll]
10 An input/output interface 1005 is further connected
to the bus 1004. An input unit 1006, an output unit 1007,
a storage unit 1008, a communication unit 1009, and a
drive 1010 are connected to the input/output interface
1005.
15 [0112]
The input unit 1006 is formed with a keyboard, a
mouse, a microphone, and the like. The output unit 1007
is formed with a display, a speaker, and the like. The
storage unit 1008 is formed with a hard disk, a
20 nonvolatile memory, or the like. The communication unit
1009 is formed with a network interface or the like. The
drive 1010 drives a removable medium 1011 such as a
magnetic disk, an optical disk, a magnetooptical disk, or
a semiconductor memory.
25 [0113]
In the computer having the above described
structure, the CPU 1001 loads the programs stored in the
storage unit 1008 into the RAM 1003 via the input/output
interface 1005 and the bus 1004, and executes the
30 programs, so that the above described series of processes
are performed.
[0114]
The programs to be executed by the computer (the
CPU 1001) may be recorded on the removable medium 1011 as
a package medium to be provided, for example.
5 Alternatively, the programs can be provided via a wired
or wireless transmission medium such as a local area
network, the Internet, or digital satellite broadcasting.
[0115]
In the computer, the programs can be installed into
10 the storage unit 1008 via the input/output interface 1005
when the removable medium 1011 is mounted on the drive
1010. Also, the programs may be received by the
communication unit 1009 via a wired or wireless
transmission medium, and be installed into the storage
15 unit 1008. Alternatively, the programs may be installed
beforehand into the ROM 1002 or the storage unit 1008.
[0116]
The programs to be executed by the computer may be
programs for performing processes in chronological order
20 in accordance with the sequence described in this
specification, or may be programs for performing
processes in parallel or performing a process when
necessary, such as when there is a call.
[0117]
25 In this specification, a system means an assembly
of components (apparatuses, modules (parts), and the
like), and not all the components need to be provided in
the same housing. In view of this, apparatuses that are
housed in different housings and are connected to each
30 other via a network form a system, and one apparatus
having modules housed in one housing is also a system.
[0118]
It should be noted that embodiments of the present
technique are not limited to the above described
embodiments, and various modifications may be made to
5 them without departing from the scope of the present
technique.
[0119]
For example, the present technique can be embodied
in a cloud computing structure in which one function is
10 shared among apparatuses via a network, and processing is
performed by the apparatuses cooperating with one another.
[0120]
The respective steps described with reference to
the above described flowcharts can be carried out by one
15 apparatus or can be shared among apparatuses.
[0121]
In a case where more than one process is included
in one step, the processes included in the step can be
performed by one apparatus or can be shared among
20 apparatuses..
[0122]
The present technique can also be in the following
forms .
(1) A signal processing apparatus including:
25 a singing enthusiasm calculating unit that
calculates a degree of singing enthusiasm formed with a
feature quantity indicating the status of singing
enthusiasm of a performer of a tune;
a harmonizing voice signal superimposition
30 determining unit that determines whether to superimpose a
harmonizing voice signal on a singing voice signal of the
performer of the tune based on the degree of singing
enthusiasm calculated by the singing enthusiasm
calculating unit; and
a harmonizing voice signal superimposing unit that
5 superimposes the harmonizing voice signal on the singing
voice signal based on a result of the determination
performed by the harmonizing voice signal superimposition
determining unit.
(2) The signal processing apparatus of (I), wherein the
10 singing enthusiasm calculating unit calculates the degree
of singing enthusiasm formed with the feature quantity
indicating the status of singing enthusiasm of the
performer based on a singing voice signal of the
performer of the tune.
15 (3) The signal processing apparatus of (1) or (2),
further including
a biological information acquiring unit that
acquires biological information about the performer,
wherein the singing enthusiasm calculating unit
20 calculates the degree of singing enthusiasm formed with
the feature quantity indicating the status of singing
enthusiasm of the performer based on the biological
information about the performer of the tune.
(4) The signal processing apparatus of any of (1) through
25 ( 3 ) , wherein the harmonizing voice signal superimposition
determining unit determines whether to superimpose the
harmonizing voice signal on the singing voice signal of
the performer of the tune by comparing the degree of
singing enthusiasm calculated by the singing enthusiasm
30 calculating unit with a singing enthusiasm threshold
value that is set with respect to the degree of singing
enthusiasm, and determines that the harmonizing voice
signal is to be superimposed on the singing voice signal
of the performer of the tune when the degree of singing
enthusiasm is higher than the singing enthusiasm
5 threshold value.
(5) The signal processing apparatus of any of (1) through
( 4 ) , further including
an excitement calculating unit that calculates a
degree of excitement of the tune based on a music audio
10 signal that is the audio signal of the tune,
wherein the harmonizing voice signal
superimposition determining unit determines whether to
superimpose the harmonizing voice signal on the singing
voice signal based on the degree of singing enthusiasm
15 calculated by the singing enthusiasm calculating unit and
the degree of excitement calculated by the excitement
calculating unit.
(6) The signal processing apparatus of any of (1) through
(5) , wherein
20 the singing enthusiasm threshold calculating unit
calculates a singing enthusiasm threshold value by using
the average value of degrees of singing enthusiasm of
performers, and
the harmonizing voice signal superimposition
25 determining unit determines whether to superimpose the
harmonizing voice signal on the singing voice signal of
the performer of the tune by comparing the degree of
singing enthusiasm calculated by the singing enthusiasm
calculating unit with the singing enthusiasm threshold
30 value that is set with respect to the degree of singing
enthusiasm and is determined by using the average value
of the degrees of singing enthusiasm of the performers,
and determines that the harmonizing voice signal is to be
superimposed on the singing voice signal of the performer
of the tune when the degree of singing enthusiasm is
5 higher than the singing enthusiasm threshold value.
(7) A signal processing system including:
an information processing apparatus that includes:
a singing enthusiasm acquiring unit that acquires
degrees of singing enthusiasm calculated by singing
10 enthusiasm calculating units from signal processing
apparatuses of any of (1) through (6) via a network, the
signal processing apparatuses including the singing
enthusiasm calculating units that calculate the degrees
of singing enthusiasm;
15 a singing enthusiasm threshold calculating unit
that calculates a singing enthusiasm threshold value by
using the average value of the degrees of singing
enthusiasm obtained by the singing enthusiasm acquiring
unit from the signal processing apparatuses; and
20 a delivering unit that delivers the singing
enthusiasm threshold value calculated by the singing
enthusiasm threshold calculating unit to the signal
processing apparatuses; and
a signal processing apparatus of any of (1) through
25 (61,
wherein the harmonizing voice signal
superimposition determining unit determines whether to
superimpose the harmonizing voice signal on the singing
voice signal of the performer of the tune by comparing
30 the degree of singing enthusiasm calculated by the
singing enthusiasm calculating unit with the singing
enthusiasm threshold value that is set with respect to
the degree of singing enthusiasm and is delivered from
the delivering unit, and determines that the harmonizing
voice signal is to be superimposed on the singing voice
5 signal of the performer of the tune when the degree of
singing enthusiasm is higher than the singing enthusiasm
threshold value.
(8) A signal processing method including:
a singing enthusiasm calculating step of
10 calculating a degree of singing enthusiasm formed with a
feature quantity indicating the status of singing
enthusiasm of a performer of a tune, the singing
enthusiasm calculating step being carried out at a
singing enthusiasm calculating unit that calculates the
15 degree of singing enthusiasm formed with the feature
quantity indicating the status of singing enthusiasm of
the performer of the tune;
a harmonizing voice signal superimposition
determining step of determining whether to superimpose a
20 harmonizing voice signal on a singing voice signal of the
performer of the tune based on the degree of singing
enthusiasm calculated by the processing in the singing
enthusiasm calculating step, the harmonizing voice signal
superimposition determining step being carried out at a
25 harmonizing voice signal superimposition determining unit
that determines whether to superimpose the harmonizing
voice signal on the singing voice signal of the performer
of the tune based on the degree of singing enthusiasm
calculated by the singing enthusiasm calculating unit;
30 and
a harmonizing voice signal superimposing step of
superimposing the harmonizing voice signal on the singing
voice signal based on a result of the determination
performed by the processing in the harmonizing voice
signal superimposition determining step, the harmonizing
5 voice signal superimposing step being carried out at a
harmonizing voice signal superimposing unit that
superimposes the harmonizing voice signal on the singing
voice signal based on a result of the determination
performed by the harmonizing voice signal superimposition
10 determining unit.
(9) A program for causing a computer to perform an
operation that includes:
a singing enthusiasm calculating step of
calculating a degree of singing enthusiasm formed with a
15 feature quantity indicating the status of singing
enthusiasm of a performer of a tune, the singing
enthusiasm calculating step being carried out at a
singing enthusiasm calculating unit;
a harmonizing voice signal superimposition
20 determining step of determining whether to superimpose a
harmonizing voice signal on a singing voice signal of the
performer of the tune based on the degree of singing
enthusiasm calculated by the processing in the singing
enthusiasm calculating step, the harmonizing voice signal
25 superimposition determining step being carried out at a
harmonizing voice signal superimposition determining
unit; and
a harmonizing voice signal superimposing step of
superimposing the harmonizing voice signal on the singing
30 voice signal based on a result of the determination
performed by the processing in the harmonizing voice
signal superimposition determining step, the harmonizing
voice signal superimposing step being carried out at a
harmonizing voice signal superimposing unit,
the computer controlling a signal processing
5 apparatus that includes:
the singing enthusiasm calculating unit that
calculates the degree of singing enthusiasm formed with
the feature quantity indicating the status of singing
enthusiasm of the performer of the tune;
10 the harmonizing voice signal superimposition
determining unit that determines whether to superimpose
the harmonizing voice signal on the singing voice signal
of the performer of the tune based on the degree of
singing enthusiasm calculated by the singing enthusiasm
15 calculating unit; and
the harmonizing voice signal superimposing unit
that superimposes the harmonizing voice signal on the
singing voice signal based on a result of the
determination performed by the harmonizing voice signal
20 superimposition determining unit.
REFERENCE SIGNS LIST
[0123]
1, 1-1 through 1-n Voice processing apparatus, 2
25 Singing enthusiasm server, 3 Music database, 4 Network,
30 DSP, 51 Singing enthusiasm calculating unit, 52 Pitch
detecting unit, 53 Harmonizing key determining unit, 54
Pitch shifter, 55 Musical excitement calculating unit, 56
Harmonizing signal controlling unit, 57 Echo effect
30 adding unit, 58 Adder

CLAIMS
1. A signal processing apparatus comprising:
a singing enthusiasm calculating unit configured to
5 calculate a degree of singing enthusiasm formed with a
feature quantity indicating a status of singing
enthusiasm of a performer of a tune;
a harmonizing voice signal superimposition
determining unit configured to determine whether to
10 superimpose a harmonizing voice signal on a singing voice
signal of the performer of the tune based on the degree
of singing enthusiasm calculated by the singing
enthusiasm calculating unit; and
a harmonizing voice signal superimposing unit
15 configured-to superimpose the harmonizing voice signal on
the singing voice signal based on a result of the
determination performed by the harmonizing voice signal
superimposition determining unit.
20 2. The signal processing apparatus according to claim
1, wherein the singing enthusiasm calculating unit
calculates the degree of singing enthusiasm formed with
the feature quantity indicating the status of singing
enthusiasm of the performer based on a singing voice
25 signal of the performer of the tune.
3. The signal processing apparatus according to claim
1, further comprising
a biological information acquiring unit configured
30 to acquire biological information about the performer,
wherein the singing enthusiasm calculating unit
calculates the degree of singing enthusiasm formed with
the feature quantity indicating the status of singing
enthusiasm of the performer based on the biological
information about the performer of the tune.
5
4. The signal processing apparatus according to claim
1, wherein the harmonizing voice signal superimposition
determining unit determines whether to superimpose the
harmonizing voice signal on the singing voice signal of
10 the performer of the tune by comparing the degree of
singing enthusiasm calculated by the singing enthusiasm
calculating unit with a singing enthusiasm threshold
value that is set with respect to the degree of singing
enthusiasm, and determines that the harmonizing voice
15 signal is to be superimposed on the singing voice signal
of the performer of the tune when the degree of singing
enthusiasm is higher than the singing enthusiasm
threshold value.
20 5. The signal processing apparatus according to claim
1, further comprising
an excitement calculating unit configured to
calculate a degree of excitement of the tune based on a
music audio signal that is an audio signal of the tune,
25 wherein the harmonizing voice signal
superimposition determining unit determines whether to
superimpose the harmonizing voice signal on the singing
voice signal based on the degree of singing enthusiasm
calculated by the singing enthusiasm calculating unit and
30 the degree of excitement calculated by the excitement
calculating unit.
6. The signal processing apparatus according to claim
1, wherein
the singing enthusiasm threshold calculating unit
5 calculates a singing enthusiasm threshold value by using
an average value of degrees of singing enthusiasm of a
plurality of performers, and
the harmonizing voice signal superimposition
determining unit determines whether to superimpose the
10 harmonizing voice signal on the singing voice signal of
the performer of the tune by comparing the degree of
singing enthusiasm calculated by the singing enthusiasm
calculating unit with the singing enthusiasm threshold
value that is set with respect to the degree of singing
15 enthusiasm and is determined by using the average value
of the degrees of singing enthusiasm of the plurality of
performers, and determines that the harmonizing voice
signal is to be superimposed on the singing voice signal
of the performer of the tune when the degree of singing
20 enthusiasm is higher than the singing enthusiasm
threshold value.
7. A signal processing system comprising:
an information processing apparatus including:
25 a singing enthusiasm acquiring unit configured to
acquire degrees of singing enthusiasm calculated by
singing enthusiasm calculating units from a plurality of
signal processing apparatuses of any of claims 1 through
4 via a network, the signal processing apparatuses
30 including the singing enthusiasm calculating units
configured to calculate the degrees of singing
enthusiasm;
a singing enthusiasm threshold calculating unit
configured to calculate a singing enthusiasm threshold
value by using an average value of the degrees of singing
5 enthusiasm obtained by the singing enthusiasm acquiring
unit from the plurality of signal processing apparatuses;
and
a delivering unit configured to deliver the singing
enthusiasm threshold value calculated by the singing
10 enthusiasm threshold calculating unit to the plurality of
signal processing apparatuses; and
a signal processing apparatus of any of claims 1
through 4,
wherein the harmonizing voice signal
15 superimposition determining unit determines whether to
superimpose the harmonizing voice signal on the singing
voice signal of the performer of the tune by comparing
the degree of singing enthusiasm calculated by the
singing enthusiasm calculating unit with the singing
20 enthusiasm threshold value that is set with respect to
the degree of singing enthusiasm and is delivered from
the delivering unit, and determines that the harmonizing
voice signal is to be superimposed on the singing voice
signal of the performer of the tune when the degree of
25 singing enthusiasm is higher than the singing enthusiasm
threshold value.
8. A signal processing method comprising:
a singing enthusiasm calculating step of
30 calculating a degree of singing enthusiasm formed with a
feature quantity indicating a status of singing
j) 3 J ~ B
enthusiasm of a performer of a tune, the singing
enthusiasm calculating step being carried out at a
singing enthusiasm calculating unit configured to
calculate the degree of singing enthusiasm formed with
5 the feature quantity indicating the status of singing
enthusiasm of the performer of the tune;
a harmonizing voice signal superimposition
determining step of determining whether to superimpose a
harmonizing voice signal on a singing voice signal of the
10 performer of the tune based on the degree of singing
enthusiasm calculated by the processing in the singing
enthusiasm calculating step, the harmonizing voice signal
superimposition determining step being carried out at a
harmonizing voice signal superimposition determining unit
15 configured to determine whether to superimpose the
harmonizing voice signal on the singing voice signal of
the performer of the tune based on the degree of singing
enthusiasm calculated by the singing enthusiasm
calculating unit; and
20 a harmonizing voice signal superimposing step of
superimposing the harmonizing voice signal on the singing
voice signal based on a result of the determination
performed by the processing in the harmonizing voice
signal superimposition determining step, the harmonizing
25 voice signal superimposing step being carried out at a
harmonizing voice signal superimposing unit configured to
superimpose the harmonizing voice signal on the singing
voice signal based on a result of the determination
performed by the harmonizing voice signal superimposition
30 determining unit.
9. A program for causing a computer to perform an
operation including:
a singing enthusiasm calculating step of
calculating a degree of singing enthusiasm formed with a
5 feature quantity indicating a status of singing
enthusiasm of a performer of a tune, the singing
enthusiasm calculating step being carried out at a
singing enthusiasm calculating unit;
a harmonizing voice signal superimposition
10 determining step of determining whether to superimpose a
harmonizing voice signal on a singing voice signal of the
performer of the tune based on the degree of singing
enthusiasm calculated by the processing in the singing
enthusiasm calculating step, the harmonizing voice signal
15 superimposition determining step being carried out at a
harmonizing voice signal superimposition determining
unit; and
a harmonizing voice signal superimposing step of
superimposing the harmonizing voice signal on the singing
20 voice signal based on a result of the determination
performed by the processing in the harmonizing voice
signal superimposition determining step, the harmonizing
voice signal superimposing step being carried out at a
harmonizing voice signal superimposing unit,
25 the computer controlling a signal processing
apparatus including:
the singing enthusiasm calculating unit configured
to calculate the degree of singing enthusiasm formed with
the feature quantity indicating the status of singing
30 enthusiasm of the performer of the tune;
the harmonizing voice signal superimposition
determining unit configured to determine whether to
superimpose the harmonizing voice signal on the singing
voice signal of the performer of the tune based on the
degree of singing enthusiasm calculated by the singing
5 enthusiasm calculating unit; and
the harmonizing voice signal superimposing unit
configured to superimpose the harmonizing voice signal on
the singing voice signal based on a result of the
determination performed by the harmonizing voice- signal
10 superimposition determining unit.
Dated this February 03,2014
(SWATI PAHUJA)
OF REMFRY & SAGAR
ATTORNEY FOR THE APPLICANT[S]