•
-1-
METHOD FOR ENTERING TEXT
FIELD OF THE INVENTION
The invention relates generally to a method
of entering text into a device. More particularly,
5 the invention relates to character input assisted
vocalized text entry into a device.
BACKGROUND OF THE INVENTION
Small computing devices such as mobile
10 phones and personal digital assistants (PDA's) are
used with an ever increasing frequency. The computing
power of these devices has allowed them to be used to
access and browse the internet as well as store
contact information, review and edit text documents,
15 and perform other tasks. Additionally, it has become
very popular to send . and receive text messages with
mobile devices. For example, The Short Message
Service (SMS) for mobile phones has been a tremendous
success in the text messaging roadmap and the
20 recently introduced Enhanced Messaging Service (EMS),
an application-level extension of SMS, is expected to
offer a smooth transition to the forthcoming
Multimedia Messaging Service (MMS). As a result,
these devices provide many applications in which text
25 entry is required. Unfortunately, such text entry on
mobile devices can be cumbersome because they lack a
standard full-sized keyboard.
achieve
Currently,
text input
there are two common
using numeric key pads
ways
found
to
on
•
-2-
most mobile phones, a multiple-tap approach, and a
single-tap approach. With the multiple-tap approach,
a user presses a numeric key a number of times to
enter the desired letter, where most of the numeric
5 keys .are mapped to three or four letters of the
alphabet. For example, the two key is usually mapped
to the letters A, B, and C. If the user presses the
two key once, the letter A is entered. If the user
presses the two key twice, the letter B is entered,
10 and if the user presses the two key three times, the
letter C is entered. Pauses between entry of
successive letters of a word are sometimes necessary
so that the device knows when to advance the cursor
to the next letter-entry position. For example, to
15 enter the word "cab," the user presses the two key
three times to enter the letter C, pauses, presses
the two key once to enter the letter A, pauses again,
and presses the two key twice to enter the letter B.
Other keys that are present on numeric keypads, such
20 as the pound("#") and asterisk("*") keys, among
other keys, are typically mapped to enter symbols, or
switch between upper-case and lower-case letters.
While the multiple-tap approach is usable
in that users can enter any word using only the
25 numeric keys, it is disadvantageous for quick and
intuitive text entry. A word such as "cab" that only
requires three key presses on a standard keyboard,
one for each letter, requires six key presses on
numeric keys using the multiple-tap approach. As
30 compared to using a standard keyboard, using numeric
•
-3-
keys with the multiple-tap approach to achieve text
entry means that the user presses many keys even for
short messages. Furthermore, errors can be frequent.
For example, if the user intends to enter the letter
5 B, but pauses too long between the first and second
presses of the two key, two letters A will be entered
instead. The device in this case interprets the pause
as the user having finished with the current letter
entry, an A, and proceeds to the next letter-entry
10 position, where it also enters an A.
Another approach to text entry using
numeric keys is the single-tap-dictionary approach,
such as "T9", popularized by a company called Tegic.
Under the single-tap approach, the user presses the
15 numeric key associated with the desired letter once,
even though the numeric key may be mapped to three or
four different letters. When the user is enters a
number sequence for a word, the device attempts to
discern the word that the user intended to enter,
20 based on the number sequence. Each number sequence is
mapped to a common word that corresponds to the
sequence. For example, the number sequence 43556 can
potentially correspond to any five-letter word having
a first letter G, H, or I, since the four key is
25 usually mapped to these letters. Similarly, the
sequence potentially corresponds to any five-letter
word having a second letter D, E, or F, a third and
fourth letter selected from the letters J, K, and L,
and a fifth letter M, N, or 0, since the three, five,
30 and six keys are usually mapped to these respective
•
-4-
letters. However, because the most common five-letter
word corresponding to the number sequence 43556 is
the word "hello," the single-tap approach may always
enter this word when the user presses the four,
5 three, five, five, and six keys in succession to
input this number sequence.
The single-tap approach has advantages over
the multiple-tap approach, but presents new
disadvantages. Advantageously, the single-tap
10 approach ensures, with a high probability, that the
user only has to press the same number of keys as the
number of letters in a desired word. For example, the
multiple-tap approach requires the user to press the
two key six times to enter the word "cab. "
15 Conversely, the single-tap approach potentially only
requires the user to press the two key three times to
enter this word, assuming that the number sequence
222 is mapped to the word "cab." Therefore, the
single-tap approach is more key-efficient than the
20 multiple-tap approach for text entry using numeric
keys. It is almost as key-efficient as using a
standard keyboard that has a single key for each
letter.
The single-tap approach is disadvantageous
25 in that the word mapped to a given number sequence
may not be the word the user intended to enter by
inputting the sequence. For example, the numeric key
sequence 7333 corresponds to both the words "seed"
and "reed." Because only one word is mapped to each
30 numeric key sequence, the word "seed" may be entered
•
-5-
when the user keys in the numeric key sequence 7333,
whereas the user may have intended to enter the word
"reed." The single-tap approach is primarily useful
where there is only one unique word for a given
5 numeric key sequence, or, if there are a number of
words for a given sequence, when the user wishes to
input the most common word associated with the
sequence. Where the word mapped by the single-tap
approach is not the intended word, text entry may
10 revert back to the multiple-tap approach or to an
error-correction mode. Ultimate text entry of the
intended word may then require more keystrokes than
if the user had started with the multiple-tap
approach.
15 Another method of entering text outside of
the use of a conventional keyboard is through the use
of a speech recognition system. In such systems, the
user vocalizes the text entry, which is captured by
the computing device through a microphone and
20 digitized. Spectral analysis is applied to samples of
the digitized captured speech and feature vectors or
code words are generated for each sample. Output
probabilities can then be computed against
statistical models such as Hidden Markov Models,
25 which are later used in executing a Viterbi decoding
process or similar type of processing technique. An
acoustic model that represents speech units is
searched to determine the likely phonemes that are
represented by the feature vectors or code words and,
30 hence, the utterance received from the user of the
•
-6-
system. A lexicon of vocalized word candidates is
searched to determined the word that most likely
represents the feature vector or code words.
Additionally, language models can be used to improve
5 the accuracy of the word produced by the speech
recognition system. Language models generally operate
to improve the accuracy of the speech recognition
system by limiting the candidate words to those that
are most likely base upon preceding words. Once the
10 words of the captured vocalized text entry are
identified, they are entered as text in the computing
system.
Speech recognition systems require
significant processing power in order to process the
15 vocalized text entry and produce reasonably accurate
results. Although mobile devices of the future may be
capable of implementing such speech recognition
systems, present mobile computing devices lack the
necessary processing power to do so in a useful
20 manner. Additionally, mobile computing devices
typically lack the memory capacity that is required
for large vocabulary continuous speech recognition.
Accordingly, mobile computing devices have relied
upon the text entry methods discussed above that
25 utilize limited keyboards.
There is a continuing demand for improved
methods of entering text into devices including
mobile computing devices.
•
-7-
SUMMARY OF THE INVENTION
The invention generally relates to a method
of entering text into a device. In the method, a
5 first character input is provided that is indicative
of a first character of a text entry. Next, a
vocalization of the text entry is captured. A
probable word candidate is then identified for a
first word of the vocalization based upon the first
10 character input and an analysis of the vocalization.
15
Finally, the probable word candidate is displayed for
a user.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 is a simplified block diagram of an
exemplary computing device in which the invention can
be used.
FIG. 2 is a schematic diagram of a mobile
phone in which the invention can be used.
20 FIG. 3 is a flowchart illustrating a method
for entering text into a device, in accordance with
embodiments of the invention.
FIG. 4 is a block diagram of a exemplary
system that can be used to implement the method of
25 the invention.
FIG. 5 is a flowchart illustrating a method
of entering text into a device in accordance with
embodiments of the invention.
•
-8-
FIG. 6 is a flowchart illustrating a method
of entering text into a device in accordance with
embodiments of the invention.
5 DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS
The present invention generally relates to
a method for entering text into computing devices.
Although the method of the present invention can be
implemented in computing devices that include a
10 conventional full-sized keyboard, it is most useful
when used in connection with mobile computing devices
that lack such a keyboard.
FIG. 1 is a block diagram of an exemplary
computing device 100 in which the invention can be
15 implemented. Device 100 can be a mobile computing
device such as, for example, a mobile phone, a
personal digital assistant (PDA), a mobile storage
system (e.g., MP3 player), a remote control, and
other mobile computing devices that lack a
20 conventional full-sized keyboard. Device 100 is only
one example of a sui table computing environment for
the present invention and is not intended to suggest
any limitation as to the scope of use or
functionality of the invention. Additionally, device
25 100 should not be interpreted as having any
dependency or requirement relating to any one or
combination of the components illustrated in FIG. 1.
Device 100 can include a controller or
processor 102, a computer or machine-readable memory
30 104, a display 106, a microphone 108, and a character
•
-9-
input device 110. Memory 104 is a machine-readable
memory that can be accessed by processor 102. Memory
104 can comprise volatile and non-volatile memory
storage technologies, and can be configured for
5 removal from device 100 or fixed therein. For
example, memory 104 can include, but is not limited
to, RAM, ROM, EEPROM, flash memory or other memory
storage device.
Memory 104 is configured to store
10 instructions, such as program modules, that can be
executed by processor 102 to implement the method of
the present invention. Generally, program modules
include routines, programs, objects, components, data
structures, etc. that perform particular tasks or
15 implement particular abstract data types. The
invention may also be practiced in distributed
computing environments where tasks are performed by
remote processing devices that are linked through a
communications network. In a distributed computing
20 environment, program modules may be located in both
local and remote memory storage devices.
Processor 102 is configured to display text
and images on display 106 in accordance with
conventional computing device operations. Display 106
25 can be any suitable display. For mobile computing
devices, display 106 is typically a small, flat
display, such as a liquid crystal display (LCD) that
can also be touch-sensitive. Alternatively, display
106 can be a larger display, such as a cathode-ray
•
-10-
tube {CRT) display, or other type of larger display,
such as a large flat panel display.
Microphone 108 of device 100 can be used by
a user to input a vocalization. The vocalization is
5 preferably converted to digital form by an analog-todigital
{A/D) converter 112. As will be discussed
below in greater detail, device 100 can process the
digitized vocalization to extract probable word
candidates that are contained in the vocalization.
10 This is generally accomplished by executing a speech
recognition or language processing module contained
in memory 104 using processor 102 to process the
digitized vocalization.
Character input device 110 is used by a
15 user to input alphanumeric characters, symbols,
spaces, etc., as a text entry into device 100.
Additionally, character input device 110 can be used
to make selections, move a cursor, scroll a page,
navigate options and menus, and perform other
20 functions. Although the character input device 110
could be a conventional keyboard, the present
invention is most useful with computing devices 100
that have a limited character input device 110 that
is generally smaller, has fewer keys, and limited
25 functionality relative to conventional full-sized
keyboards. Inputting characters using such limited
character input devices 110 can be slow and
cumbersome.
Limited character input devices 110 can
30 take on many different forms. Some limited character
•
-11-
input devices 110, which are typically used by PDA's,
are formed by a touch-sensitive display, such as
display 106. One such character-input device 110 is
formed by displaying a miniature keyboard on the
5 touch-sensitive display 106. The user can select the
desired characters for text entry by touching the
displayed character with a stylus in a similar manner
as a conventional keyboard. Another such character
input device 110 allows users to write characters on
10 the display 106 or by designating input characters
that are each mapped to a particular sequence of
strokes that can be applied to touch-sensitive
display 106 using the stylus. Once the user provides
the text entry using either form of the input device
15 110, the text entry is provided on display 106.
Mobile computing devices, such as mobile
phones, utilize a limited character input device 110
in the form of a numeric keypad. FIG. 2 is a
simplified diagram of a device 100 in the form of a
20 mobile phone 114 that includes such a numeric keypad
116, a display 106 and a microphone 108. Mobile phone
114 can also includes a speaker 118, an antenna 120
as well as communications circuitry in the form of a
transceiver (not shown) and other components, which
25 are not pertinent to the present invention.
Numeric keypad 116 includes a number of
numeric keys 122 and other keys. In general, numeric
keypad 116 is distinguished from a standard keyboard
in that it does not have a unique key for each
30 character. As a result, numeric keypad 116 is a
•
-12-
limited character input device 110. Keypad 116 has
the following number of keys: a one key 122A, a two
key 122B, a three key 122C, a four key 122D, a five
key 122E, a six key 122F, a seven key 122G, an eight
5 key 122H, a nine key 122I, and a zero key 122J.
Numeric keypad 116 also has an asterisk (*) key 122K,
and a pound sign (#) key 122L. Numeric keypad 116 may
also have other specialized keys beyond those shown
in FIG. 2, or fewer keys than those shown in FIG. 2.
10 The keys 122 of numeric keypad 116 may be real,
physical keys, or virtual, soft keys displayed on
display 106, where display 106 is a touch-sensitive
screen.
All of the number keys 122 of numeric
15 keypad 116, except for the one key 122A and the zero
key 122J, correspond to three or four letters of the
alphabet. The two key 122B corresponds to letters A,
B, and C. The three key 122C corresponds to the
letters D, E, and F. The four key 122D corresponds to
20 the letters G, H, and I. The five key 122E
corresponds to the letters J, K, and L. The six key
122F corresponds to the letters M, N, and 0. The
seven key 122G corresponds to the letters P, Q, R,
and S. The eight key 122H corresponds to the letters
25 T, U, and V. Finally, the nine key 122I corresponds
to the letters w, X, Y, and z. Punctuation characters
and symbols may be included either on unused keys,
such as the one key 122A, or may be also included on
the other number keys 122, along with the letters.
•
-13-
Additionally, each number key 122 can be used to
enter the number or symbol that is labeled thereon.
Mobile computing devices of the prior art,
such as mobile phones, use the multiple-tap and
5 single-tap methods to enter text into the device 100.
Such methods can be cumbersome and inefficient, not
only because of the need to provide at least one
entry using keys 122 for each character of the text.
Additionally, the single-tap method that often fails
10 to recognize the word the user is trying to enter.
For example, to enter the word "hello" the user
presses the four key 122D, the three key 122C, the
five key 122E twice and the six key 122F in
succession. Because the number sequence entered 43556
15 may correspond to other words than the word "hello",
the intended word is ambiguous. Additionally, the
lexicon used by the device, which contains words that
are matched to specific number sequences, may not
contain the word that is desired to be entered by the
20 user. This generally results in an out-of-vocabulary
(OOV) error, which generally requires that the user
change the text entry mode of the device from singletap
mode to multiple-tap mode and reenter the desired
text entry from the beginning. As a result, the user
25 may be forced to perform significantly more numeric
key presses the number of letters contained in the
word.
The present invention operates to
significantly reduce the number of key presses that
3 0 are required to enter the desired text into device
•
-14-
100 as compared to the methods of the prior art. This
is accomplished through a combination of speech
recognition with user input. The result is a text
entry system that is simple, efficient and accurate.
5 FIG. 3 is a flowchart illustrating steps of
the method in accordance with various embodiments of
the invention. FIG. 4 is a block diagram of an
exemplary system 128 that can be used to implement
embodiments of the method on device 100. The
10 components of system 128 generally correspond to
program modules and instructions that are contained,
for example, in memory 104 and are executable by
processor 102 of FIG. 1 to perform the various steps
of the method.
15 While the device 100 is set to a text entry
mode, a first character input 130 is provided by the
user, at step 132. The first character input 130 is
indicative of the first character of a text entry
that is desired to be input by the user. For example,
20 when the desired text entry is "BERRY" the user
provides a first character input 130 that is
indicative of the letter "B".
The first character input 130 can be the
actual first character of the text entry that is
2 5 directly input by the user using, for example, the
multiple-tap method on numeric keypad 116 (FIG. 2), a
touch-sensitive display, a conventional keyboard,
another type of input device 110 (FIG. 1), or other
means. One disadvantage of this embodiment of the
30 invention is that limited character input devices
•
-15-
110, such as the numeric keypad 116 may force the
user to press a key 122 multiple times to enter the
desired character, as explained above.
The first character input 130 can also be
5 entered by the user in accordance with the single-tap
method. Thus, for numeric keypad 116 the user must
only press the key 122 corresponding to the desired
character once. Thus, to enter "B" the user must
simply press the two key 122B once. In accordance
10 with this embodiment of the invention, the first
character input 130 is representative of "B" as well
as "A and "C".
At step 134 of the method, a vocalization
136 of the text entry is captured. This is generally
15 accomplished by the user speaking the text entry into
microphone 108, which is digitized by A/D converter
112 and stored in memory 104 or otherwise processed
by processor 102, in accordance with conventional
speech recognition methods. Preferably, the
20 vocalization 136 is captured after the first
character input 130 has been provided by the user.
25
The capturing of the vocalization 136 can
be triggered to begin
Preferably, an indicator
in many different ways.
is provided by device 100
on, for example,
vocalization of
display 106, to inform the user that
the text entry should begin. In
accordance with one embodiment of the invention, the
capturing step 134 begins in response to the user
providing the first character input 130 at step 132
30 of the method. Accordingly, for the single-tap input
•
-16-
method, the pressing of the numeric key corresponding
to the first character of the text entry while in the
text entry mode of the device 100 begins the
capturing step 134. In accordance with another
5 embodiment of the invention, the capturing step 134
begins with the pressing and holding of a key of the
character input device 110. This is particularly
useful for the single-tap method where only a single
key is pressed to designate the first character input
10 130, but can be implemented along with the multipletap
and other text entry input methods. Device 100
can also include a dedicated hard or soft key that is
used to trigger the capturing step 132.
15 the
In accordance with another
invention, the capturing step
embodiment of
134 may be
configured to compensate situations where a user
prematurely speaks before a key press or other
vocalization capture triggering event is detected.
One way to address this issue is to continuously
20 buffer a few hundred milliseconds of any vocalization
by the user in memory 104 while device 100 operates
in the text entry mode. The buffered vocalization can
be used to capture a "false start" vocalization of
the text entry that began prior to the triggering
25 event, which can be included as part of the
vocalization input 136 that is provided to the speech
recognizer 142 (Fig. 4) during the capturing step
134.
The capturing step 134 can be terminated by
30 either the expiration of a predetermined period of
•
-17-
time or by the release of the button or key that was
held to begin the capture of the vocalized text
entry. Alternatively, the capturing step 132 can be
terminated after the system detects the termination
5 of the vocalization of the text entry. When the
capturing step 132 is terminated, device 100
preferably provides notice of such to the user such
as by terminating the indicator that was provided
upon the commencement of the capturing step 132.
10 In accordance with one embodiment of the
invention, the text entry provided by the user must
be in isolated or single word increments.
Accordingly, the vocalization 136 of the text entry
corresponds to the single or isolated text entry
15 word. The process of entering text by selecting a
first character input and speaking or vocalizing a
single text entry word is somewhat natural when the
single-tap method is used to enter the first
character input 13 0. Additionally, single word text
20 entry has its advantages in the mobile computing
device context. In particular, less memory is
required to temporarily store the captured
vocalization 136. Additionally, less computational
power is required to analyze the vocalization 136 and
25 more accurate speech recognition results are
possible, as will be discussed below.
In accordance with another embodiment of
the invention, the text entry is provided by the user
in the form of multiple words. Due to the generally
30 limited memory capacity and processing power of
•
-18-
mobile computing devices, the length of the text
entry is preferably limited. Accordingly, the user is
preferably only allowed to enter a short phrase or
sentence. In accordance with one embodiment of the
5 invention, the indicator that notifies the user of
the start and end to the capturing step can be in the
form of a timer (i.e., countdown timer) or the
display of a bar that extends to indicate the elapse
of time and the end of the capturing step 134. Both
10 the single word and multiple word text entry
embodiments of the present invention initially
operate in substantially the same manner with respect
to the first word of the text entry and the
corresponding first word of the vocalization.
15 At step 138 of the method, a probable word
candidate 140 is identified for a first word of the
vocalization 13 6 of the text entry based upon the
first character input 130 and an analysis of the
vocalization 136. In general, the method operates to
20 narrow a list of potential word candidates for the
first word of the text entry (multiple word text
entry mode) or the text entry word (single or
isolated text entry mode) through the elimination of
words that fail to match the criteria set forth by
25 the first character input 130. For example, when a
single-tap first character input 130 corresponds to
multiple characters "ABC", for example, the list of
potential word candidates can be pruned down to only
those words that begin with either "A," "B," or "C".
30 As a result, the system 128 of device 100 can not
•
-19-
only produce more accurate results, but can produce
results much more quickly than would be possible if
all potential word candidates for the vocalization
136 were analyzed. This is particularly beneficial
5 for mobile computing devices 100 that lack the
processing power used by other computing systems that
implement speech recognition systems.
The analysis of the vocalization 136 is
generally performed by a speech recognizer 142 (FIG.
10 4}. Speech recognizer 142 generally performs spectral
analysis on digital samples of the vocalization 136
to identify a list of probable word candidates 144
from a lexicon or list of vocalized word candidates
146 that most likely correspond to the vocalization
15 136 of the text entry. Preferably the list of
probable word candidates 144 produced by speech
recognizer 142 are ranked in accordance with their
likelihood of matching the vocalization 136.
Speech recognizer 142 can also include a
20 language model 148 that can improve the accuracy of
speech recognizer 142. Language model 148 operates to
specify which sequences of words in the vocabulary
are possible, or in general, provides information
about the likelihood of various word sequences.
25 Examples of language models are 1-gram, 2-gram, and
N-gram language models. The 1-gram language model
considers only the individual word probability,
whereas the 2-gram language model considers the
preceding word in the text entry as having an
30 influence on what the current vocalized word of the
•
-20-
text entry is. Similarly, the 3-gram, 4-gram and Ngram
language models consider the immediate two,
three or N-1 words preceding the desired text entry
in determining a match with the vocalization 136. Due
5 to the general lack of processing power in mobile
computerized devices 100, it may be necessary to
limit the language model 148 to 1- or 2-gram language
models.
The identifying step 138 is generally
10 performed by a predictor module 150. In accordance
with one embodiment of the invention, the predictor
15
module 150 receives the list of probable word
candidates 144 and the character input 130. The
predictor module 148 identifies the probable word
candidate 140 from the list of probable word
candidates 144 based upon the first character input
130. Predictor 150 preferably selects the highest
ranked word in the list of probable word candidates
144 having the character input 130 as its first
20 letter, as the probable word candidate 140.
In accordance with another embodiment of
the invention, the identifying step 138 is performed
by first narrowing the lexicon or list of vocalized
word candidates 146 of the speech recognizer 142
25 using the first character input 130, as indicated by
dashed line 152 in FIG. 4. As a result, the list of
vocalized word candidates 146 is reduced to a
narrowed list of vocalized word candidates 154 by
eliminating all of the vocalized word candidates that
30 fail to begin with the character or characters
•
-21-
identified by the first character input 130. The
narrowed list of vocalized word candidates 154 is
further narrowed to form the list of probable word
candidates 144 for the first word of the vocalization
5 13 6 based upon an analysis by the speech recognizer
142. As a result, the list of probable word
candidates 144 that are provided to predictor 150
each begin with the character or characters
identified by the character input 130. Predictor 150
10 then identifies the probable word candidate 140,
which is preferably the highest ranked candidate in
the list of probable word candidates 144.
Another embodiment of the identifying step
138 includes performing a single-tap analysis on the
15 first character input 130. In general, the predictor
150 uses the first character input 130 to narrow a
lexicon or list of input word candidates 156 to only
those words having first characters that correspond
to the first character input 130. In this manner, the
20 list of input word candidates 156 is reduced to a
narrowed list of input word candidates 158 for the
first word of the vocalization 136. The predictor 150
then compares the list of vocalized word candidates
144 that are produced in response to the analysis of
25 the vocalization 136 by the speech recognizer 142 to
the narrowed list of input word candidates 158.
Predictor 150 then identifies the probable word
candidate 140 as the word candidate that is located
in both the list of vocalized word candidates and the
30 narrowed list of input word candidates. Preferably,
•
-22-
the predictor 150 selects the probable word candidate
140 as the word having the highest rank in the list
of probable word candidates 144 that has a match in
the narrowed list of input word candidates 158.
5 In the final step 160 of the method, the
probable word candidate 140 is displayed for the user
on, for example, display 106 of device 100.
Alternatively, multiple probable word candidates can
be displayed for the user that satisfy the
10 identifying step 138. The displaying of the probable
word can be construed as an entry of the probable
word candidate into device 100 even though it has yet
to be accepted by the user.
The displayed probable word 140 can then be
15 accepted to complete the text entry of the word or
rejected by the user. Generally, the probable word
candidate 140 is accepted and entered as the text
entry into device 100 in response to a selection by
the user. In accordance with one embodiment of the
20 invention, the user enters the displayed probable
word candidate 140 by pressing a hard or soft key on
device 100. In accordance with one embodiment of the
invention, the selection by the user is preferably
performed by pressing one of the keys 122 of the
25 numeric keypad that does not correspond to
alphanumeric characters, such as the asterisk key
122K or the pound symbol key 122L. However, it should
be understood that many conventional methods for
making a selection can be used to enter the displayed
30 probable word candidate.
•
-23-
When the user is entering text one word at
a time and the displayed probable word is accepted by
the user and entered, the method can continue in
accordance with the flowchart of FIG. 5. At step, 162
5 the user provides a second character input that is
indicative of a first character of a second text
entry. The second character input can be provided in
accordance with the procedures explained above for
providing first character input 130. Next, at step
10 164, a vocalization of the second text entry is
captured in the manner described above with respect
to step 134 {FIG. 3). A probable word candidate is
then identified for the vocalization of the second
text entry, at step 166, based upon the second
15 character input and an analysis of the vocalization
of the second text entry. This step is performed
substantially in the manner described above with
respect to step 138 of the method of FIG. 3. Finally,
the probable word candidate for the vocalization of
20 the second text entry is displayed at step 168. The
user then has the options of selecting or
the displayed probable word candidate as
above.
rejecting
described
The language model 146 of the speech
25 recognizer 150 can take into account preceding words
in the text entry to identify the current word that
the user is attempting to enter. Accordingly, the
step 166 of identifying a probable word candidate for
the vocalization of the second text entry can be
•
-24-
further based upon the previously entered probable
word candidate 140.
When the user is entering text in the
multiple word format, the displayed probable word is
5 accepted by the user, and the words of the
vocalization 136 have not all been identified, the
method can continue in accordance with the flowchart
of FIG. 6. At step 170 of the method, a second
character input is provided that is indicative of a
10 first letter of a second word of the vocalization 136
captured in step 134 of the method of FIG. 3. As
mentioned above, the second character input can be
provided in accordance with the procedures explained
above for providing first character input 130. Next,
15 at step 172, a probable word candidate for the second
word of the vocalization 136 is identified based on
an analysis of the vocalization 136 and the second
character input. The probable word candidate is then
displayed at step 174 for the user to either accept
20 or reject. If the user accepts this probable word
candidate, the method returns to step 170 and repeats
until the words of the vocalization 136 are
identified. As above, the step 172 of identifying a
probable word candidate for the second word of the
25 vocalization can be further based on the previously
entered probable word candidate 140 using an
appropriate language model 146 of speech recognizer
150.
30
As mentioned
opportunity to reject
above, the user also has an
the displayed probable word
•
-25-
candidate 140 by providing a suitable input. In
accordance with one embodiment of the invention, a
key is provided by device 100 that, when pressed,
results in the rejection of the displayed probable
5 word candidate 140. Such a key can be a soft key or a
hard key of device 100. For example, where the
asterisk key 122K is used to accept a displayed
probable word candidate 140, the pound symbol key
122L can be used to reject the displayed probable
10 word candidate. Many other methods of rejecting the
displayed probable word candidate can be used as
well.
In accordance with one embodiment of the
invention, upon rejection of the probable word
15 candidate by the user, one or more alternative
probable word candidates that match the criteria of
the identifying step 138 (FIG. 3) are displayed for
the user in accordance with their rank. For example,
when the desired word to be entered is "BURY", the
20 probable word 140 displayed by the system 128 could
be "BERRY". After the user rejects the displayed
probable word, system 128 can display the most likely
alternatives, such as the desired word "BURY" as well
as "BARRY," for example. The user then is provided an
25 option to select between the displayed alternative
probable word candidates.
In accordance with another embodiment of
the invention, the rejection of the displayed
probable word candidate 140 occurs in response to the
30 user providing a second character input that is
•
-26-
indicative of a second character of the first word of
the vocalization 136 of the desired text entry. The
entry of the second character input can be made in
the manner described above for the first character
5 input 130. The system 128 of device 100 locates one
or more alternative probable word candidates that
satisfy the method implemented in step 138 (FIG. 3)
and have first and second characters that correspond
to the first and second character inputs. The
10 alternative probable word candidates can then be
displayed to the user for selection or rejection.
This process can repeat by continuing to enter the
third and subsequent characters of the text entry.
In the event that the displayed alternative
15 probable words still fail to match the text entry
word desired by the user, the mode of text entry for
device 100 can be switched to the multiple-tap mode
to allow the user to enter the desired word directly
into device 100.
20 Although the present invention has been
described with reference to particular embodiments,
workers skilled in the art will recognize that
changes may be made in form and detail without
departing from the spirit and scope of the invention.
25 Also, although most of the discussion here is
centered around alphabetical languages such as
English, those skilled in the art will recognize that
the principles outlined in this invention are also
applicable to other languages such as those in the
East Asia whose input methods are not based on
alphabets.

•
-28-
WHAT IS CLAIMED IS:
1. A method of entering text into a device
comprising:
a) providing a first character input that
is indicative of a first character of
a text entry word;
b) capturing a vocalization of the text
entry word;
c) identifying a probable word candidate
for the vocalization based upon the
first character input and an analysis
of the vocalization; and
d) displaying the probable word
candidate.
2. The method of claim 1, wherein the
capturing step b) begins in response to the providing
step a) .
3 . The method of claim 1, wherein the
capturing step b) begins prior to the providing step
a) .
4. The method of claim 1, wherein the
capturing step b) ends after a predetermined period
of time.
5. The method of
capturing step b) ends
vocalization is detected.
claim 1, wherein
after an end to
the
the
•
-29-
6 . The method of claim
includes
1 1 wherein
pressing a
the
providing step a) key
corresponding to multiple characters.
7. The method of claim 1 1 wherein:
the providing step a) includes pressing and
holding a key; and
the capturing step b) begins in response to
the providing step a) .
8. The method of claim 7 I wherein the
capturing step b) ends after a predetermined period
of time.
9. The method of claim 7 I wherein the
capturing step ends when the key is released.
10. The method of claim 11 wherein the
identifying step c) includes:
11.
producing a
candidates
list of probable word
based upon an analysis of
the vocalization; and
identifying the probable word candidate
from the list of probable word
candidates for the vocalization based
on the first character input.
The method of claim 10 including:
•
-30-
rejecting the probable word candidate in
response to an input by a user; and
displaying an alternative probable word
candidate from the list of probable
word candidates.
12. The method of claim 1, wherein the
identifying step c) includes:
13.
narrowing a list of vocalized word
candidates using the first character
input to form a narrowed list of
vocalized word candidates;
narrowing the narrowed list of vocalized
word candidates to a list of probable
word candidates for the vocalization
based upon an analysis of the
vocalization; and
identifying the probable
from the list of
candidates.
word candidate
probable word
The method of claim 12 including:
rejecting the probable word candidate in
response to an input by a user; and
displaying an alternative probable word
candidate from the list of probable
word candidates.
14. The method of claim 1, wherein the
identifying step c) includes:
•
15.
16.
-31-
analyzing the vocalization to produce a
list of vocalized word candidates;
narrowing a list of input word candidates
using the first character input to
form a narrowed list of input word
candidates for the vocalization;
comparing the list of vocalized word
candidates to the narrowed list of
input word candidates; and
identifying the probable word candidate as
a word candidate that is located in
both the list of vocalized word
candidates and the narrowed list of
input word candidates.
The method of claim 14 including:
rejecting the probable word candidate in
response to an input by a user; and
displaying an alternative probable word
candidate that is located in both the
list of vocalized word candidates and
the narrowed list of input word
candidates.
The method of claim 1 including providing a
second character input that is indicative of a second
character of the text entry word, wherein the
probable word candidate identified in step c) is
based on the first and second character inputs and
the analysis of the vocalization.
•
17.
the
The method
probable word
-32-
of claim
candidate
1 including entering
in response to a
selection by a user.
18. The method of claim 17 including:
providing a second character input that is
indicative of a first character of a
second text entry word;
capturing a vocalization of the second text
entry word;
identifying a probable word candidate for
the vocalization of the second text
entry word based upon the second
character input and an analysis of the
vocalization of the second text entry
word; and
displaying the probable word candidate for
the vocalization of the second text
entry word.
19. The method of claim 18, wherein the step of
identifying a probable word candidate for the
vocalization of the second text entry word is further
based on the entered probable word candidate.
20. A method of entering text into a device
comprising:
•
-33-
a) providing a first character input that
is indicative of a first character of
a text entry;
b) capturing a vocalization of the text
entry;
c) identifying a probable word candidate
for a first word of the vocalization
based upon the first character input
and an analysis of the vocalization;
and
d) displaying the probable word
candidate.
21. The method of claim 20, wherein the text
entry consists of a single word.
22. The method of claim 20, wherein the text
entry comprises multiple words.
23. The method of claim 20, wherein the
capturing step b) begins in response to the providing
step a) .
24. The method of claim 23, wherein the
capturing step b) ends after a predetermined period
of time.
2 5 . The method
providing step a)
of claim
includes
20, wherein
pressing a
corresponding to multiple characters.
the
key
•
-34-
26. The method of claim 20, wherein:
the providing step a) includes pressing and
holding a key; and
the capturing step b) begins in response to
the providing step a) .
27. The method of claim 26, wherein the
capturing step b) ends after a predetermined period
of time.
28. The method of claim 26, wherein the
capturing step b) ends when the key is released.
29. The method of claim 20, wherein the
identifying step c) includes:
30.
producing a list of probable word
candidates based upon an analysis of
the vocalization; and
identifying the probable word candidate
from the list of probable word
candidates for the first word of the
vocalization based upon the
character input.
The method of claim 29, including:
first
rejecting the probable word candidate in
response to an input by a user; and
•
-35-
displaying an alternative probable word
candidate from the list of probable
word candidates.
31. The method of claim 20, wherein the
identifying step c) includes:
32.
narrowing a
candidates
input to
list
using
form
of vocalized word
the first character
a narrowed list of
vocalized word candidates;
narrowing the narrowed list of vocalized
word candidates to form a list · of
probable word candidates for the first
word of the vocalization based upon an
analysis of the vocalization; and
identifying the probable word candidate
from the list of probable word
candidates.
The method of claim 31 including:
rejecting the probable word candidate in
response to an input by a user; and
displaying an alternative probable word
candidate from the list of probable
word candidates.
33. The method of claim 20, wherein the
identifying step c) includes:
analyzing the vocalization to produce a
list of vocalized word candidates;
•
34.
-36-
narrowing a list of input word candidates
using the first character input to
form a narrowed list of input word
candidates for the first word of the
vocalization;
comparing the list of vocalized word
candidates to the narrowed list of
input word candidates; and
identifying the probable word candidate as
a word candidate that is located in
both the list of vocalized word
candidates and the narrowed list of
input word candidates.
The method of claim 33 including:
rejecting the probable word candidate in
response to an input by a user; and
displaying an alternative probable word
candidate that is located in both the
list of vocalized word candidates and
the narrowed list of input word
candidates.
35. The method of claim 20 including providing
a second character input that is indicative of a
second character of the text entry, wherein the
probable word candidate identified in step c) is
based on the first and second character inputs, and
the analysis of the vocalization.
•
36.
the
-37-
The method of claim 2 0
probable word candidate
including entering
in response to a
selection by a user.
37. The method of claim 36 including:
providing a second character input that is
indicative of a first character of a
second text entry;
capturing a vocalization of the second text
entry;
identifying a probable word candidate for
the vocalization of the second text
entry based upon the second character
input and an analysis of the
vocalization of the second text entry;
and
displaying the probable word candidate for
the vocalization of the second text
entry.
38. The method of claim 37, wherein the step of
identifying a probable word candidate for the
vocalization of the second text entry is further
based on the entered probable word candidate.
39. The method of claim 36 including:
providing a second character input that is
indicative of a first character of a
second word of the vocalization;

40.identifying a probable word candidate for
the second word of the vocalization
based upon the second character input
and an analysis of the vocalization;
and
displaying the probable word candidate for
the second word of the vocalization.
The method of claim 39, wherein the step of
identifying a probable word candidate for the second
word of the vocalization is further based on the
entered probable word candidate.
41 A method of entering text into a device substantially as
hereinbefore described with reference to the accompanying drawings.