Description:A METHOD AND A VOICE ASSISTANT SYSTEM FOR GENERATING A VOICE COMMAND
TECHNICAL FIELD
[0001] The present subject matter relates to a field of Voice Assistant (VA) system in a vehicle. More specifically, the present subject matter relates to a method and a VA system for generating a voice command by using a reference signal generated based on a number of real-time parameters.

BACKGROUND
[0002] Traditionally, existing VA systems work by taking feedback from amplifiers output i.e., actual audio signal, using speaker position microphones for each speaker or deep neural based that is big data trained system that can take decision to control the amplifier output on its own based on only mic input. The existing VA systems use actual feedback signal of all speakers from amplifier to audio unit as additional Input/ Output (I/O) pins of a head unit are required due to limitation in audio system I/O as well as complexity in harness.
[0003] A conventional solution discloses a system that utilizes a music sound signal output by speaker amplifier as the original reference signal. Further, a music sound signal elimination module obtains information regarding phase, time domain and frequency information of the reference signal, and perform inversion processing to obtain the internal signal. The music sound signal is synchronized in the de-noised sound signal, and an amplitude to the size of the reference signal is modified.
[0004] Another conventional solution discloses a system that discloses an adaptive volume and EQ setting adjustment of sound by estimating the magnitude and type of noise generated. The system includes at least one mic and an acoustic control system apparatus. The control system may identify noise as normal or abnormal on the basis of source, frequency and loudness.
[0005] Another conventional solution discloses a system including an array mic and a voice recognition module. The system is configured to perform a sound source localization by a technique of beamforming.
[0006] Yet another conventional solution discloses a system including a car audio system, microphone arrays, an external amplifier, speakers, a voice signal processing unit with sound canceller. The voice processing device and the vehicular devices are connected to a cloud via a wireless communication network. A voice recognition server is provided on the cloud. The voice signal processing unit uses adaptive filtering techniques and cancels out music that is picked up being mixed through the speaker position microphone after being emitted by the vehicular speakers. The reproduction sound canceller adds the dummy audio signal for the reproduction music generated by the adaptive filter to a voice signal collected by a speaker position microphone by means of the adder.
[0007] FIG. 1 illustrates an architectural diagram 100 depicting a system for generating a voice command in a vehicle, in accordance with an existing prior art. A feedback signal may be required for each speaker for voice recognition by a VA system within a head unit due to mixing of speaker noise. The feedback signal is generated by an external amplifier thereby an external hardware is to generate the reference signal. The reference signal is not generated inside a head unit of the vehicle.
[0008] There is a need for a solution to overcome above mentioned drawbacks.
OBJECT OF THE DISCLOSURE
[0009] A primary object of the present subject matter is to generate a voice command received from a user.
[0010] Another object of the present subject matter is to negate an external noise for generating the voice command.
[0011] Yet another object of the present subject matter is to generate a reference signal inside a head unit for negating the external noise.
SUMMARY
[0012] This summary is provided to introduce concepts related to a method and a VA system for generating a voice command. The concepts are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
[0013] In an embodiment, the present subject matter provides a method implemented by a VA system in a vehicle for generating a voice command. The method includes receiving, by a microphone, a plurality of sound signals as a plurality of voice inputs simultaneously with one another. The plurality of voice inputs comprises a first voice input received from a user and a second voice input received from at least one speaker. The method includes generating, by a generation engine, a reference signal resembling the second voice input, based on a plurality of real-time parameters. The plurality of real-time parameters is associated with the plurality of voice inputs and the vehicle. The method includes processing, by a processing engine, the plurality of voice inputs with the reference signal by performing a phase inversion. The reference signal negates the second voice input from the at least one speaker during the phase inversion. The method includes generating, by the processing engine, the first voice input as the voice command.
[0014] In an embodiment, the present subject matter provides a VA system implemented in a vehicle for generating a voice command. The VA system includes a microphone configured to receive a plurality of sound signals as a plurality of voice inputs simultaneously with one another. The plurality of voice inputs comprises a first voice input received from a user and a second voice input received from at least one speaker. The VA system includes a generation engine configured to generate a reference signal resembling the second voice input, based on a plurality of real-time parameters. The plurality of real-time parameters is associated with the plurality of voice inputs and the vehicle. The VA system includes a processing engine configured to process the plurality of voice inputs with the reference signal by performing a phase inversion. The reference signal negates the second voice input from the at least one speaker during the phase inversion. The processing engine is further configured to generate the first voice input as the voice command.
[0015] In an aspect of the present subject matter, the plurality of sound signals is converted into a plurality of electrical signal by the microphone prior to processing of the plurality of voice inputs.
[0016] In an aspect of the present disclosure, the reference signal is an electrical signal.
[0017] In an aspect of the present disclosure, the plurality of real-time parameters comprises a flat output associated with a head unit of the vehicle, a tuned Equalizer (EQ) file, a real-time volume of the second voice input, and one or more vehicle parameters.
[0018] In an aspect of the present disclosure, the second voice input is generated by receiving, by a Digital Signal Processor (DSP), from one or more external sources,, one or more audio signals as one or more audio inputs, transmitting, by the DSP, the one or more audio signals to an external amplifier, processing, by the external amplifier, the one or more audio signals to convert the one or more audio signals into the electrical signal, and generating, by the external amplifier via the at least one speaker, the electrical signal as the second voice input.
[0019] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF THE FIGURES
[0020] The illustrated embodiments of the subject matter will be best understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
[0021] FIG. 1 illustrates an architectural diagram depicting a system for generating a voice command in a vehicle, in accordance with an existing prior art;
[0022] FIG. 2 illustrates a block diagram depicting a method implemented by a Voice Assistant (VA) system in a vehicle for generating a voice command, in accordance with an embodiment of the present subject matter;
[0023] FIG. 3 illustrates a schematic block diagram depicting a VA system for generating a voice command, in accordance with an embodiment of the present subject matter;
[0024] FIG. 4 illustrates an operational flow diagram depicting a process for implemented in a vehicle for generating a voice command, in accordance with an embodiment of the present subject matter;
[0025] FIG. 5 illustrates a diagram depicting an implementation of the VA system for generating the voice command, in accordance with an embodiment of the present subject matter; and
[0026] FIG. 6 illustrates a block diagram depicting generation of a voice command, in accordance with an embodiment of the present subject matter.

DETAILED DESCRIPTION
[0027] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
[0028] As used in the description herein and throughout the claims that follow, the meaning of “a”, “an”, and “the” includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.
[0029] FIG. 2 illustrates a block diagram depicting a method 200 implemented by a Voice Assistant (VA) system in a vehicle for generating a voice command, in accordance with an embodiment of the present subject matter. The method 200 may be implemented in a vehicle and may be associated with speech recognition. In a preferred embodiment, the method 200 may be implemented in an infotainment system incorporated in the vehicle.
[0030] At block 202, the method 200 includes receiving, by a microphone, a plurality of sound signals as a plurality of voice inputs simultaneously with one another, wherein the plurality of voice inputs comprises a first voice input received from a user and a second voice input received from at least one speaker..
[0031] At block 204, the method 200 includes, generating, by a generation engine, a reference signal based on a plurality of real-time parameters, wherein the plurality of real-time parameters is associated with the plurality of voice inputs and the vehicle.
[0032] At block 206, the method 200 includes, processing, by a processing engine, the plurality of voice inputs with the reference signal by performing a phase inversion, wherein the reference signal negate the second voice input from the at least one speaker during the phase inversion.
[0033] At block 208, the method 200 includes, generating, by the processing engine, the first voice input as the voice command
[0034] FIG. 3 illustrates a schematic block diagram 300 depicting a VA system 302 implemented in a vehicle for generating a voice command, in accordance with an embodiment of the present subject matter. The voice command may be generated from a first user input. The VA system 302 may be configured to negate an external noise received as a second voice input for generating the voice command by processing the external noise with a reference signal. The VA system 302 may utilise an intelligent system to negate the external noise.
[0035] The VA system 302 may include a microphone 304, a generation engine 306, a processing engine 308, an external amplifier 310, at least one speaker 312 connected to the external amplifier 310, and , and a Digital Signal Processor (DSP) 314. The microphone 304, the generation engine 306, the processing engine 308, the external amplifier 310, the at least one speaker 312, and the DSP 314 may be communicably coupled to one another.
[0036] The microphone 304 may be configured to receive a number of sound signals simultaneously with one another. The number of sound signals may be received as a number of voice inputs. The number of voice inputs may include the first voice input and the second voice input. The first voice input may be a user command received from a user in a vicinity of the VA system 302. Further, the second voice input may be the external noise received from the at least one speaker 312. In a preferred embodiment, the VA system 302 may include 8 speakers.
[0037] To that understanding, for generating the second voice input, the DSP 314 may be configured to receive one or more audio signals as one or more audio inputs from one or more external sources. Examples of the one or more sources may include, but are not limited to, a Universal Serial Bus (USB) slot such that an audio is being played on the number of speakers 312 using the USB, an Over The Top (OTT) platform, a navigation prompt, and a prompt from an electronic device. In an exemplary embodiment, the one or more audio signals may be received via the microphone 304. Further, the DSP 314 may be configured to transmit the one or more audio signals to the external amplifier 310. Moving forward, the external amplifier 310 may be configured to process the one or more audio signals to convert the one or more audio signals into the electrical signal. Furthermore, the external amplifier 310 may be configured to generate via the at least one speaker 312, the electrical signal as the second voice input.
[0038] In response to receiving the number of sound signals, the microphone 304 may be configured to process the number of sound signals in order to convert each sound signal from the number of sound signals into an electrical signal, thus generating a number of electrical signals. Further, the microphone 304 may be configured to transmit the number of voice inputs in a form of the number of electrical signals to the processing engine 308.
[0039] Continuing with the above embodiment, the generation engine 306 may be configured to generate the reference signal. The reference signal may be a feedback signal resembling the second voice input received from the at least one speaker 312. The reference signal may be generated in a form of an electrical signal. The generation engine 306 may be an intelligent engine configured generate the reference signal. The reference signal may be generated based on a number of real-time parameters. The number of real-time parameters may be related to each of the number of voice inputs and the vehicle. Examples of the number of real-time parameters may include, but are not limited to, a flat output associated with a head unit of the vehicle, a tuned Equalizer (EQ) file, a real-time volume of the second voice input, and one or more vehicle parameters.
[0040] To that understanding, the processing engine 308 may be configured to process the number of voice inputs with the reference signal. For processing the number of voice inputs, the processing engine 308 may be configured to perform a phase inversion. While performing the phase inversion, the processing engine 308 may be configured to negate the second voice input with the reference signal. Negating the second voice input received from the at least one speaker 312 may reduce the external noise received with the first voice input such that the first voice input is enhanced.
[0041] Continuing with the above embodiment, the processing engine 308 may be configured to generate the first voice input as the voice command. The voice command may be clear and amplified as the second voice input is negated with the reference signal.
[0042] FIG. 4 illustrates an operational flow diagram depicting a process 400 for implemented in a vehicle for generating a voice command, in accordance with an embodiment of the present subject matter. The process 400 may be implemented by the VA system 302 as referred in the fig. 3. Furthermore, the voice command may be generated from a first user input. The process 400 may be associated with speech recognition. In a preferred embodiment, the process 400 may be implemented in an infotainment system incorporated in the vehicle. The process 400 may include negating an external noise received as a second voice input for generating the voice command. external
[0043] At step 402, the process 400 may include receiving a number of sound signals simultaneously with one another. The number of sound signals may be received by the microphone 304 as referred in the fig. 3. The number of sound signals may be received as a number of voice inputs. The number of voice inputs may include the first voice input and the second voice input received from a user and the at least one speaker 312. For generating the second voice input, the process 400 may include receiving by the DSP 314 as referred in the fig. 3, one or more audio signals as one or more audio inputs from one or more external sources. Examples of the one or more sources may include, but are not limited to, a Universal Serial Bus (USB) slot such that an audio is being played on the number of speakers 312 using the USB, an Over The Top (OTT) platform, a navigation prompt, and a prompt from an electronic device. In an exemplary embodiment, the one or more audio signals may be received via the microphone 304. Further, the process 400 may include transmitting the one or more audio signals to the external amplifier 410 as referred in the fig. 3. The external amplifier 310 may be configured to convert the one or more audio signals into the electrical signal. Furthermore, the external amplifier 310 may be configured to generate via the at least one speaker 312, the electrical signal as the second voice input.
[0044] At step 404, the process 400 may include processing the number of sound signals. The number of signals may be processed by the microphone 304. Processing the number of signals may include converting each sound signal from the number of sound signals into an electrical signal, thereby generating a number of electrical signals.
[0045] At step 406, the process 400 may include transmitting by the microphone 404, the number of voice inputs in a form of the number of electrical signals to the processing engine 308.
[0046] At step 408, the process 400 may include generating a reference signal. The reference signal may be generated by the generation engine 306 as referred in the fig. 3. The reference signal may be generated in a form of an electrical signal. based on a number of real-time parameters. The number of real-time parameters may be related to each of the number of voice inputs and the vehicle. Examples of the number of real-time parameters may include, but are not limited to, a flat output associated with a head unit of the vehicle, a tuned Equalizer (EQ) file, a real-time volume of the second voice input, and one or more vehicle parameters. The one or more vehicle parameters may include a speed and a mode of the vehicle. The mode may indicate whether the vehicle is in a cruise mode, a hill mode, and the like.
[0047] At step 410, the process 400 may include processing the number of voice inputs with the reference signal. The processing may be performed by the processing engine 308 as referred in the fig. 3. For processing the number of voice inputs, the process 400 may include performing a phase inversion. The phase inversion may include negating the second voice input with the reference signal such Negating the second voice input received from the at least one speaker 312 may cancel the external noise received with the first voice input such that the first voice input is enhanced.
[0048] At step 412, the process 400 may include generating by the processing engine 308 the first voice input as the voice command. The voice command may be clear and amplified as the second voice input is negated with the reference signal.
[0049] FIG. 5 illustrates a diagram 500 depicting an implementation of the VA system 302 for generating the voice command, in accordance with an embodiment of the present subject matter. The microphone 304 may be configured to receive a number of voice inputs including a first voice input and a second voice input. The number of voice inputs may be received in a form of a sound signal. The first voice input may be received from a user and the second voice input may be received from the at least one speaker 312 such that the second voice input may be an output of the at least one speaker 312.
[0050] For generating the second voice input, the DSP 314 may be configured to receive one or more audio signals from one or more external sources. Examples of the one or more sources may include, but are not limited to, a Universal Serial Bus (USB) slot such that an audio is being played on the number of speakers 312 using the USB, an Over The Top (OTT) platform, a navigation prompt, and a prompt from an electronic device. In an exemplary embodiment, the one or more audio signals may be received via the microphone 304 Further, the DSP 314 may be configured to transmit the one or more audio signals to the external amplifier 310. The external amplifier 310 may be configured to convert the one or more audio signals into the electrical signal. Furthermore, the external amplifier 310 may be configured to generate via the at least one speaker 312, the electrical signal as the second voice input.
[0051] Moving forward, the microphone 304 may be configured to convert each sound signal from the number of sound signals into an electrical signal, thus generating a number of electrical signals. Further, the microphone 304 may be configured to transmit the number of voice inputs in a form of the number of electrical signals to the processing engine 308.
[0052] The generation engine 306 may be configured to generate a reference signal in a form of an electrical signal. The reference signal may be generated based on a number of real-time parameters. The number of real-time parameters may be related to each of the number of voice inputs and the vehicle. Examples of the number of real-time parameters may include, but are not limited to, a flat output associated with a head unit of the vehicle, a tuned Equalizer (EQ) file, a real-time volume of the second voice input, and one or more vehicle parameters.
[0053] The processing engine 308 may be configured to process the number of voice inputs received from the microphone 304, with the reference signal. The processing may include negating the second voice input with the reference signal by performing a phase inversion. Negating the second voice input received from the at least one speaker 312 may reduce the external noise received with the first voice input such that the first voice input is enhanced.
[0054] The processing engine 308 may be configured to generate the first voice input as the voice command. The voice command may be clear and amplified as the second voice input is negated with the reference signal.
[0055] FIG. 6 illustrates a block diagram 600 depicting generation of a voice command, in accordance with an embodiment of the present subject matter. The voice command may be generated based on a first voice input received from a user. The generation engine 306 may receive a number of real-time parameters associated with a number of voice inputs and a vehicle. Examples of the number of real-time parameters may include, but are not limited to, a flat output associated with a head unit of the vehicle, a tuned EQ file, a real-time volume of the second voice input, and one or more vehicle parameters. Further, the generation engine 306 may be configured to generate a reference signal resembling a second voice input amongst the number of voice inputs. The first voice input and the second voice input may be received by the microphone 304. Further, the second voice input may be received from the at least speaker 312. The second voice input may be an external noise received along with the first voice input amongst the number of voice input.
[0056] Moving forward, the generation engine 306 may be configured to transmit the reference signal to the processing engine 308. Further, the processing engine 308 may be configured to process the number of voice inputs with the reference signal. Processing the number of voice inputs may include negating the second voice input with the reference signal, thereby enhancing the first voice input and generating the first voice input as the voice command. The second voice input may be negated by performing a phase inversion.
[0057] Furthermore, all examples recited herein are principally intended expressly to be only for pedagogical purposes to aid the reader in understanding the principles of the invention and the concepts contributed by the inventor(s) to furthering the art and are to be construed as being without limitation to such specifically recited examples and conditions. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments.
[0058] While the detailed description describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions, or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
, Claims:We claim:
1. A method (200) implemented by a Voice Assistant (VA) system (302) in a vehicle for generating a voice command, the method (200) comprising:
receiving (102), by a microphone (304), a plurality of sound signals as a plurality of voice inputs simultaneously with one another, wherein the plurality of voice inputs comprises a first voice input received from a user and a second voice input received from at least one speaker (312);
generating (104), by a generation engine (306), a reference signal resembling the second voice input, based on a plurality of real-time parameters, wherein the plurality of real-time parameters is associated with the plurality of voice inputs and the vehicle;
processing (106), by a processing engine (308), the plurality of voice inputs with the reference signal by performing a phase inversion, wherein the reference signal negates the second voice input from the at least one speaker (312) during the phase inversion; and
generating (108), by the processing engine (308), the first voice input as the voice command.
2. The method (200) as claimed in claim 1, wherein the plurality of sound signals is converted into a plurality of electrical signal by the microphone (304) prior to processing of the plurality of voice inputs.
3. The method (200) as claimed in claim 1, wherein the reference signal is an electrical signal.
4. The method (200) as claimed in claim 1, wherein the plurality of real-time parameters comprises a flat output associated with a head unit of the vehicle, a tuned Equalizer (EQ) file, a real-time volume of the second voice input, and one or more vehicle parameters.
5. The method (200) as claimed in claim 1, wherein the second voice input is generated by:
receiving, by a Digital Signal Processor (DSP) (314), from one or more external sources, one or more audio signals as one or more audio inputs in the vehicle;
transmitting, by the DSP (314), the one or more audio signals to an external amplifier (310);
processing, by the external amplifier (310), the one or more audio signals to convert the one or more audio signals into the electrical signal; and
generating, by the external amplifier (310) via the at least one speaker (312), the electrical signal as the second voice input.
6. A VA system (302) implemented in a vehicle for generating a voice command, the VA system (302) comprising:
a microphone (304) configured to receive a plurality of sound signals as a plurality of voice inputs simultaneously with one another, wherein the plurality of voice inputs comprises a first voice input received from a user and a second voice input received from at least one speaker (312);
a generation engine (306) configured to generate a reference signal resembling the second voice input, based on a plurality of real-time parameters, wherein the plurality of real-time parameters is associated with the plurality of voice inputs and the vehicle; and
a processing engine (308) configured to:
process the plurality of voice inputs with the reference signal by performing a phase inversion, wherein the reference signal negates the second voice input from the at least one speaker (312) during the phase inversion; and
generate the first voice input as the voice command.
7. The VA system (302) as claimed in claim 6, wherein the plurality of sound signals is converted into a plurality of electrical signal by the microphone (304) prior to processing of the plurality of voice inputs.
8. The VA system (302) as claimed in claim 6, wherein the reference signal is an electrical signal.
9. The VA system (302) as claimed in claim 6, wherein the plurality of real-time parameters comprises a flat output associated with a head unit of the vehicle, a tuned Equalizer (EQ) file, a real-time volume of the second voice input, and one or more vehicle parameters.
10. The VA system (302) as claimed in claim 6, wherein the second voice input is generated by:
the DSP 314 configured to:
receive from one or more external sources, one or more audio signals as one or more audio inputs in the vehicle; and
transmit the one or more audio signals to an external amplifier (310); and
the external amplifier (310) configured to:
process the one or more audio signals to convert the one or more audio signals into the electrical signal; and
generate via the at least one speaker (312), the electrical signal as the second voice input.