DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/29/2026 was filed after the mailing date of the Non-Final Rejection on 05/06/2026. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
1. Regarding the rejection under 35 U.S.C. 101, Applicant's arguments filed 07/29/2026 have been fully considered but they are not persuasive.
Applicant argues that the claims do not recite mental processes under Step 2A Prong 1, specifically that the extraction steps cannot be performed in the human mind with the aid of pen and paper (see pg. 8, 2nd para. of Remarks). The Examiner respectfully disagrees. The amended claims still recite abstract ideas in the form of mental processes under Step 2A Prong 1. The recited steps of processing first and second audio data to extract first and second spatial sector audio data representing first and second spatial sectors can be read as a mental process. Specifically, a person can write down information about what they hear in a first and second audio to generate first and second spatial sector audio data characterizing what they hear in a first and second spatial sector/area of an audio scene. For example, a person can write down first audio information they hear in a first spatial sector (i.e. to their left, or in a first zone) and can write down second audio information that they hear in a second spatial sector (i.e. to their right, or in a second zone). The level of detail recited currently in amended claim 1 does not preclude these extraction steps, as well as the generating output data step, from being performed in the human mind with the aid of pen and paper. Thus, the amended claims recite mental processes under Step 2A Prong 1.
Applicant further argues that the amended claims integrate the judicial exception into a practical application via a technical improvement, specifically that recited plurality of machine-learning models used to extract spatial sector audio data leads to an improvement to audio processing via computation efficiency and reduced model complexity. The Examiner respectfully disagrees. The amended claims do not integrate the judicial exception into a practical application as the additional elements when viewed with the amended claims as a whole amount to generic computer components and do not reflect a technical improvement. Regarding amended claim 1, the additional elements recited are the plurality of machine learning models, the use of a first machine learning model, the use of a second machine learning model, and the device and second device. Each of these limitations is recited at a high level of generality and amount to merely performing the mental processes recited using generic computer components. The machine learning models are merely being used to broadly extract first and second spatial sector audio data which a person can do at the level that is currently being recited in the claim language. Furthermore, it is unclear how exactly the machine-learning models are used for a practical application. The outputs of the first and second machine-learning models are used to merely generate generic “output data” that is sent to a second device (generic computer component). The use of the claimed machine-learning models to generate generic data does not constitute a practical application or a technical improvement. Therefore, the claims do not integrate the judicial exception into a practical application under Step 2A Prong 2.
Hence, Applicant’s arguments are not persuasive.
2. Regarding the rejection under 35 U.S.C. 103, Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
3. Claims 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claims 1, 14, and 20, “A device”, “A method”, and “A non-transitory computer-readable medium” are recited, which are each directed to one of the four statutory categories of invention (machine, process, article of manufacture; Step 1: YES). However, the claims limitations, under their broadest reasonable interpretation, recite mental processes which fall into the category of abstract idea (Step 2A Prong 1: YES).
The following limitations, under their broadest reasonable interpretation, recite mental processes:
…extract spatial sector audio data that represents a respective spatial sector of a plurality of spatial sectors of an audio scene: a person writes down audio data relating to spatial audio they hear (i.e. audio they hearing coming from their left, right, or a particular area)
…process first audio data to extract first spatial sector audio data, wherein the first audio data represents the plurality of spatial sectors of the audio scene, and wherein the first spatial sector audio data represents a first spatial sector of the plurality of spatial sectors of the audio scene: a person writes down audio data relating to a first audio data they hear from a first area/zone (e.g. writes down what they hear coming from their left)
…process second audio data to extract second spatial sector audio data, wherein the second audio data represents the plurality of spatial sectors of the audio scene, wherein the second spatial sector audio data represents a second spatial sector of the plurality of spatial sectors of the audio scene, and wherein the second spatial sector is distinct from the first spatial sector: a person writes down audio data relating to a second audio data they hear
generate output data based on the first spatial sector audio data, the second spatial sector audio data, or both: a person writes down output data based on either/both of the audio data
Claims 1, 14, and 20 do not contain any additional elements which integrate the judicial exception into a practical application (Step 2A Prong 2: NO). The only additional limitations are “A device comprising: a memory configured to store a plurality of machine-learning models, wherein each of the plurality of machine-learning models is configured to extract… (claim 1); and one or more processors configured to” (claim 1), “A non-transitory computer-readable medium stores instructions that, when executed by one or more processors, cause the one or more processors to” (claim 20), “wherein each of the plurality of machine-learning models is configured to extract…” (claims 14 and 20), “use a first machine-learning model to process…” (claims 1, 14, and 20) and “use a second machine-learning model to process…” (claims 1, 14, and 20), and “send the output data to a second device“ (claims 1, 14, and 20). These limitations are recited at a high level of generality and amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claim as a whole, the additional limitations which recite mere instructions to implement the judicial exception using a generic computer do not integrate the judicial exception into a practical application as they do not impose any meaningful limits on practicing the abstract ideas. Therefore, claims 1, 14, and 20 are directed to an abstract idea.
Claims 1, 14, and 20 do not contain any additional elements which amount to significantly more than the judicial exception (Step 2B: NO). As discussed above, the only additional limitations amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claim as a whole, additional limitations which recite mere instructions to implement the judicial exception using a generic computer do not amount to significantly more than the judicial exception as they do not provide an inventive concept. Therefore, claims 1, 14, and 20 are not patent eligible.
Regarding claims 2-13 and 15-19, “The device” and “The method” are recited, which are each directed to one of the four statutory categories of invention (machine, process, article of manufacture; Step 1: YES). However, the claims limitations, under their broadest reasonable interpretation, recite further mental processes or mathematical concepts which fall into the category of abstract idea (Step 2A Prong 1: YES).
The following limitations, under their broadest reasonable interpretation, recite further mental processes or mathematical concepts:
Claims 2 and 15:
generate a first sound metric of the first spatial sector audio data: a person writes down a first sound metric for the first audio (e.g. the level of quality)
generate a second sound metric of the second spatial sector audio data: a person writes down a second sound metric for the second audio
and based on a comparison of the first sound metric and the second sound metric, select one of the first spatial sector audio data or the second spatial sector audio data as the output data: a person selects/makes a determination of which audio data to select based on comparing the metrics (e.g. which has a higher value)
Claims 3 and 16:
wherein a sound metric includes a signal-to-noise ratio (SNR): determining an SNR sound metric amounts to a mathematical calculation
Claims 4 and 17:
wherein a sound metric includes a speech quality metric, a speech intelligibility metric, or both: determining a speech quality/intelligibility metric, or both, amounts to mathematical calculcations
Claims 5 and 18:
Claims 5 and 18 recite “generate the output data based on sensor input from a sensor”. This amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 6 and 19:
select…one of the first spatial sector audio data or the second spatial sector audio data as the output data: a person can decide to select a first or second audio as the output (e.g. based on which has a higher perceived quality)
Claims 6 and 19 recite “select, based on the sensor input”, which amounts to further mere instructions to implement the judicial exception using a generic computer.
Claim 7:
select, …, the first spatial sector and the second spatial sector: responsive to selection of the first spatial sector, … extract the first spatial sector audio data; and responsive to selection of the second spatial sector, … to extract the second spatial sector audio data: a person chooses a first or second audio data, and writes down first and second spatial sector data in response to choosing the first or second audio data respectively
Claim 7 recites “select, based on the sensor input”, “use the first machine-learning model to generate”, and “use the second machine-learning model to generate”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claim 8:
Claim 8 recites “wherein the sensor includes a gyroscope, a camera, a microphone, or a combination thereof, and wherein the sensor input indicates a phone orientation, a detected sound source, a detected occlusion, or a combination thereof”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claim 9:
…perform noise suppression on the first spatial sector audio data based on the second spatial sector audio data to generate the output data: performing noise suppression amounts to a mathematical calculation
Claim 9 recites “based on the sensor input indicating that a first sound source is detected in the first spatial sector and a second sound source is detected in the second spatial sector”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claim 10:
obtain, from the first spatial sector audio data, first spatial sector first subband audio data and first spatial sector second subband audio data; obtain, from the second spatial sector audio data, second spatial sector first subband audio data and second spatial sector second subband audio data: obtaining subbands for audio data signals amounts to mathematical calculations
perform noise suppression on the first spatial sector first subband audio data based on second spatial sector first subband audio data to generate first subband noise suppressed audio data; perform noise suppression on the first spatial sector second subband audio data based on second spatial sector second subband audio data to generate second subband noise suppressed audio data: performing noise suppression on audio subband signals amounts to mathematical calculations
and generate the output data based on the first subband noise suppressed audio data and the second subband noise suppressed audio data: a person can write down output data relating to the first and second suppressed audio data
Claim 11:
Claim 11 recites “a microphone array configured to generate the first audio data and the second audio data”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claim 12:
Claim 12 recites “wherein a first subset of the microphone array is configured to generate the first audio data, and wherein a second subset of the microphone array is configured to generate the second audio data”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claim 13:
a beamformer configured to process audio data to generate the first audio data and the second audio data: beamforming signal processing amounts to a mathematical calculation
Claims 2-13 and 15-19 do not contain any additional elements which integrate the judicial exception into a practical application (Step 2A Prong 2: NO). As discussed above, the only additional limitations amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claim as a whole, the additional limitations which recite mere instructions to implement the judicial exception using a generic computer do not integrate the judicial exception into a practical application as they do not impose any meaningful limits on practicing the abstract ideas. Therefore, claims 2-13 and 15-19 are directed to an abstract idea.
Claims 2-13 and 15-19 do not contain any additional elements which amount to significantly more than the judicial exception (Step 2B: NO). As discussed above, the only additional limitations amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claim as a whole, additional limitations which recite mere instructions to implement the judicial exception using a generic computer do not amount to significantly more than the judicial exception as they do not provide an inventive concept. Therefore, claims 2-13 and 15-19 are not patent eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
4. Claims 1-6, 8, 11, and 13-20 are rejected under 35 U.S.C. 103 as being unpatentable over Cutler et al. (US 2024/0406621 A1, hereinafter Cutler) in view of Premont et al. (US 2019/0073999 A1, hereinafter Premont).
Regarding claim 1, Cutler discloses A device (Fig. 1, 150) comprising: a memory configured to store… (para. 0032 “The devices may also have various modules that function using the processing and storage resources to perform the techniques discussed herein. The storage resources can include both persistent storage resources, such as magnetic or solid-state drives, and volatile storage, such as one or more random-access memory devices. In some cases, the modules are provided as executable instructions that are stored on persistent storage devices, loaded into the random-access memory devices, and read from the random-access memory by the processing resources for execution.”); and one or more processors configured to (para. 0084 “The term “device”, “computer,” “computing device,” “client device,” and or “server device” as used herein can mean any type of device that has some amount of hardware processing capability and/or hardware storage/memory capability. Processing capability can be provided by one or more hardware processors (e.g., hardware processing units/cores) that can execute computer-readable instructions to provide functionality.”): …extract first spatial sector audio data, the first spatial sector audio data associated with a first spatial sector, wherein the first audio data represents the plurality of spatial sectors of the audio scene, and wherein the first spatial sector audio data represents a first spatial sector of the plurality of spatial sectors of the audio scene (1st spatial audio data one of audio captured from one of device 110, 120, 130, and 140 in different locations; one of the audios is a first spatial sector audio represents a first spatial sector (i.e. area/location) of an audio scene: (para. 0054); para. 0050 “As described more below, signals from microphones 402(1), 402(2), and 402(3) on individual client devices can be processed using the teleconferencing architecture 400 for playback on loudspeakers 404(1), 404(2), and 404(3) of other client devices.”; Fig. 2A shows receiving of microphone signals (212, 222, 232, etc.)); …extract second spatial sector audio data, wherein the second audio data represents the plurality of spatial sectors of the audio scene, wherein the second spatial sector audio represents a second spatial sector of the plurality of spatial sectors of the audio scene, and wherein the second spatial sector is distinct from the first spatial sector (2nd spatial audio data one of audio captured from one of device 110, 120, 130, and 140 in different locations (para. 0054); one of the audios is a second spatial sector audio represents a second spatial sector (i.e. area/location) of an audio scene; since the device locations are different, the second audio’s spatial sector is different form the first spatial sector: para. 0050 “As described more below, signals from microphones 402(1), 402(2), and 402(3) on individual client devices can be processed using the teleconferencing architecture 400 for playback on loudspeakers 404(1), 404(2), and 404(3) of other client devices.”; Fig. 2A shows receiving of microphone signals (212, 222, 232, etc.)); generate output data based on the first spatial sector audio data, the second spatial sector audio data, or both (para. 0061 “Method 500 continues at block 504, where a microphone subset is selected based on respective signal characteristics of the multiple microphone signals.”; para. 0062 “Method 500 continues at block 506, where a playback signal is obtained from one or more microphone signals output by the selected microphone subset. In cases where the selected microphone subset includes multiple microphones, the microphone signals can be synchronized and mixed to produce the playback signal.”); and send the output data to a second device (para. 0063 “Method 500 continues at block 508, where the playback signal is sent to a remote device. For instance, the remote device can be located in a different room, and the playback signal can be sent to the remote device over a network. In some cases, the playback signal can be sent to multiple remote devices, either co-located (e.g., together in a different room) or in different locations from one another.”).
Cutler does not specifically disclose:
[a memory configured to store] a plurality of machine-learning models, wherein each of the plurality of machine-learning models is configured to extract spatial sector audio data that represents a respective spatial sector of a plurality of spatial sectors of an audio scene;
use a first machine-learning model of the plurality of machine-learning models to process first audio data to extract [first spatial sector audio data…]
use a second machine-learning model of the plurality of machine-learning models to process second audio data to extract [second spatial sector audio data…]
Premont teaches [a memory configured to store] a plurality of machine-learning models, wherein each of the plurality of machine-learning models is configured to extract spatial sector audio data that represents a respective spatial sector of a plurality of spatial sectors of an audio scene (plurality of speech recognition machine learning models each extract audio data (i.e. wakup word information) based on the spatial sector: para. 0035 “According to some embodiments, speech recognition models used by units 116a, 116b, . . . , 116n may have different acoustic models. Each of the speech recognition models are used to each detect a wake-up word within one particular acoustic zone…”; para. 0033 “According to some embodiments, each of the units 116a, 116b, . . . , 116n may produce a measure (e.g., a confidence value) that the wake-up word was spoken within their associated acoustic zone and the wake-up word recognizer 110 may identify, from these measures, which acoustic zones are candidates for a valid wake-up word detection and/or which acoustic zone is the most likely candidate for a wake-up word detection.”; para. 0075 “Techniques utilized herein may be utilized with any type of automatic speech recognition techniques such as, but not limited to, speaker independent or speaker dependent models, deep neural networks…”; see Fig. 1, 116a-116c and Fig. 2, 220a-d for spatial zone specific speech recognition machine learning models);
use a first machine-learning model of the plurality of machine-learning models to process first audio data to extract [first spatial sector audio data…] (e.g., Fig. 1, use 116a to process first audio data 114a using first model 116a to extract first spatial sector audio data (i.e. output ASR data): para. 0035 “According to some embodiments, speech recognition models used by units 116a, 116b, . . . , 116n may have different acoustic models. Each of the speech recognition models are used to each detect a wake-up word within one particular acoustic zone…”; para. 0033 “According to some embodiments, each of the units 116a, 116b, . . . , 116n may produce a measure (e.g., a confidence value) that the wake-up word was spoken within their associated acoustic zone and the wake-up word recognizer 110 may identify, from these measures, which acoustic zones are candidates for a valid wake-up word detection and/or which acoustic zone is the most likely candidate for a wake-up word detection.”);
use a second machine-learning model of the plurality of machine-learning models to process second audio data to extract [second spatial sector audio data…] ((e.g., Fig. 1, use 116a to process second audio data 114b using second model 116b to extract first spatial sector audio data (i.e. output ASR data): para. 0035 “According to some embodiments, speech recognition models used by units 116a, 116b, . . . , 116n may have different acoustic models. Each of the speech recognition models are used to each detect a wake-up word within one particular acoustic zone…”; para. 0033 “According to some embodiments, each of the units 116a, 116b, . . . , 116n may produce a measure (e.g., a confidence value) that the wake-up word was spoken within their associated acoustic zone and the wake-up word recognizer 110 may identify, from these measures, which acoustic zones are candidates for a valid wake-up word detection and/or which acoustic zone is the most likely candidate for a wake-up word detection.”));
Cutler and Premont are considered to be analogous to the claimed invention as
they both are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler to incorporate the teachings of Premont in order to specifically store a plurality of machine-learning models, wherein each of the plurality of machine-learning models is configured to extract spatial sector audio data that represents a respective spatial sector of a plurality of spatial sectors of an audio scene, to use a first machine-learning model of the plurality of machine-learning models to process first audio data to extract first spatial sector audio data, and to use a second machine-learning model of the plurality of machine-learning models to process second audio data to extract second spatial sector audio data. Doing so would be beneficial, as different acoustic zones may exhibit different acoustic environments, and thus each model can be trained to specifically target a particular acoustic zone in order to improve performance and to handle such differences in acoustic environments (Premont, para. 0035).
Regarding claim 2, Cutler in view of Premont discloses generate a first sound metric of the first spatial sector audio data (Cutler, para. 0061 “Method 500 continues at block 504, where a microphone subset is selected based on respective signal characteristics of the multiple microphone signals. As noted previously, the signal characteristics can include signal-to-noise ratios of the microphone signals, speech quality characteristics of the microphone signals as determined by a machine learning model, etc.”; para. 0067 “Another approach for evaluating the quality of a given microphone signal involves employing a trained machine learning model….For instance, a trained machine learning model can estimate signal characteristics such as speech quality, background noise, and overall signal quality on a frame-by-frame basis for each microphone signal.”); generate a second sound metric of the second spatial sector audio data (Cutler, para. 0067 “Another approach for evaluating the quality of a given microphone signal involves employing a trained machine learning model….For instance, a trained machine learning model can estimate signal characteristics such as speech quality, background noise, and overall signal quality on a frame-by-frame basis for each microphone signal.”); and based on a comparison of the first sound metric and the second sound metric, select one of the first spatial sector audio data or the second spatial sector audio data as the output data (Cutler, para. 0066 “Referring back to FIGS. 2A-2C, in some cases, N can be 1. Assuming that N is statically defined as 1, then one way to select which microphone to use is simply to pick the microphone with the highest sound (e.g., speech) quality at any given time…”).
Regarding claim 3, Cutler in view of Premont discloses wherein a sound metric includes a signal-to-noise ratio (SNR) (Cutler, para. 0066 “As noted previously, one way to evaluate the sound quality of a given signal is to use the signal-to-noise ratio…”).
Regarding claim 4, Cutler in view of Premont discloses wherein a sound metric includes a speech quality metric, a speech intelligibility metric, or both (Cutler, para. 0066 “Referring back to FIGS. 2A-2C, in some cases, N can be 1. Assuming that N is statically defined as 1, then one way to select which microphone to use is simply to pick the microphone with the highest sound (e.g., speech) quality at any given time…”; para. 0067 “For instance, a trained machine learning model can estimate signal characteristics such as speech quality…”).
Regarding claim 5, Culter in view of Premont discloses to generate the output data based on sensor input form a sensor (Cutler, para. 0035 “In some cases, the playback signal module 153 can perform proximity-based mixing. For instance, if any two client devices are not in proximity to one another, the playback signal module can send playback signals to these client devices that include microphone signals from the other device. …Once the server determines that any two client devices are co-located, the playback signal module can adjust the audio mix by omitting the microphone signals from these two devices from the playback signals sent thereto.”; para. 0033 “In some cases, the proximity detection module can be configured to estimate whether other devices are in the same room. Thus, for instance, proximity detection module 113(1) on client device 110 can detect when client device 120 arrives in the same room as client device 110, e.g., based on a sound or radio frequency signal emitted by proximity detection module 113(2) on client device 120.”; para. 0056 “Thus, in some cases, sound can be employed to determine whether two client devices should be treated as co-located for mixing purposes. For instance, client device 110 can play an audio clip at an ultrasound frequency at a designated volume, and client device 120 can listen for that sound.”).
Regarding claim 6, Cutler in view of Premont discloses to select, based on the sensor input, one of the first spatial sector audio data or the second spatial sector audio data as the output data (Fig. 4, initial subset of microphones determined: para. 0061 “Method 500 continues at block 504, where a microphone subset is selected based on respective signal characteristics of the multiple microphone signals.”; sensor input (e.g. determining if a device is proximate/co-located) is used to further omit signals/select only particular signals: para. 0035 “Once the server determines that any two client devices are co-located, the playback signal module can adjust the audio mix by omitting the microphone signals from these two devices from the playback signals sent thereto. This is feasible because users in the same room should be able to hear each other speak without playback by the teleconferencing client application 111. Said another way, the playback signal delivered to a particular client device can be adjusted by the playback signal module to omit microphone signals from other client devices that are in proximity to that particular client device, as described more below.”).
Regarding claim 8, Cutler in view of Premont discloses wherein the sensor includes a gyroscope, a camera, a microphone, or a combination thereof (para. 0054 “In other cases, location information can be employed to automatically infer that two or more devices are co-located. For instance, in some cases, each client device can report its location to the server 150, as determined using local device sensors, such as Global Positioning System sensors, accelerometers, gyroscopes, or Wi-Fi based positioning.”), and wherein the sensor input indicates a phone orientation, a detected sound source, a detected occlusion, or a combination thereof (para. 0033 “Thus, for instance, proximity detection module 113(1) on client device 110 can detect when client device 120 arrives in the same room as client device 110, e.g., based on a sound or radio frequency signal emitted by proximity detection module 113(2) on client device 120.”; para. 0056 “Thus, in some cases, sound can be employed to determine whether two client devices should be treated as co-located for mixing purposes. For instance, client device 110 can play an audio clip at an ultrasound frequency at a designated volume, and client device 120 can listen for that sound.”).
Regarding claim 11, Cutler in view of Naylor discloses further comprising a microphone array configured to generate the first audio data and second audio data (Premont, para. 0019 “In some embodiments, acoustic information from an environment that has been logically partitioned into a plurality of acoustic zones may be captured by multiple microphones (e.g., a microphone array) for which the spatial relationship between the microphones is known.”; see Fig. 1, 105).
Cutler and Premont are considered to be analogous to the claimed invention as
they both are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler to incorporate the teachings of Premont in order to further comprise a microphone array configured to generate the first audio data and the second audio data. Doing so would be beneficial, as microphone arrays would enable beamforming which allow for speech signals to be received with less noise and less reverberation.
Regarding claim 13, Cutler in view of Naylor discloses further comprising a beamformer configured to process the audio data to generate the first audio data and the second audio data (Premont, para. 0019 “Acoustic information captured by the multiple microphones may be compared, filtered or otherwise processed to identify from which acoustic zone captured sound originated. For example, any of various techniques including, but not limited to, time of flight, angle of arrival, differences in amplitude, beamforming and/or other spatial filtering techniques may be utilized to identify acoustic input originating from each of the plurality of acoustic zones.”).
Cutler and Premont are considered to be analogous to the claimed invention as
they both are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler to incorporate the teachings of Premont in order to further comprise a beamformer configured to process the audio data to generate the first audio data and the second audio data. Doing so would be beneficial given the same rationale as claim 11.
Regarding claim 14, claim 14 is a method claim with limitations similar to those recited in device claim 1, and is thus rejected under similar rationale.
Regarding claim 15, claim 15 is rejected for analogous reasons to claim 2.
Regarding claim 16, claim 16 is rejected for analogous reasons to claim 3.
Regarding claim 17, claim 17 is rejected for analogous reasons to claim 4.
Regarding claim 18, claim 18 is rejected for analogous reasons to claim 5.
Regarding claim 19, claim 19 is rejected for analogous reasons to claim 6.
Regarding claim 20, claim 20 is a non-transitory computer readable media claim with limitations similar to those recited in device claim 1, and is thus rejected under similar rationale.
Additionally, Cutler discloses A non-transitory computer-readable medium stores instructions that, when executed by one or more processors, cause the one or more processors to (para. 0085 “In contrast, the term “computer-readable storage media” excludes signals.”; para. 0110 “Another example includes a computer-readable storage medium storing executable instructions which, when executed by a processor, cause the processor to perform acts comprising…”).
5. Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Cutler in view of Premont, and further in view of Naylor et al. (US 2022/0262343 A1, hereinafter Naylor).
Regarding claim 7, Cutler in view of Premont disclose to use the first machine-learning model to extract the first spatial sector audio data and to use the second machine-learning model to extract the second spatial sector audio data (see above claim mapping for claim 1), but does not specifically disclose to select, based on the sensor input, the first spatial sector and the second spatial sector; responsive to selection of the first spatial sector, [use the first machine-learning model to extract the first spatial sector audio data]; and responsive to selection of the second spatial sector, [use the second machine-learning model to extract the second spatial sector audio data].
Naylor teaches to select, based on the sensor input, the first spatial sector and the second spatial sector (detection and steering of beams towards one or more speakers (e.g. two): para. 0035 “As shown in the example of FIG. 3, microphone array 300 may be configured to receive one or more speech signals (e.g., speech signal 308) from one or more speakers (e.g., speaker 310).”; para. 0039 “In another example, suppose the beamformer formed by a microphone array is configured for adaptive beamforming and beamsteering by dynamically modifying and steering the beampattern(s) toward a speaker. In this example, beamsteering may introduce acoustic variations to the speech signal.”; sensor input collected: para. 0095 “In some implementations, speech processing process 11 may receive 718 one or more run-time inputs indicative of at least one of: a relative location of the speaker and the microphone array, and a relative orientation of the speaker and the microphone array. As discussed above and referring again to the example of FIG. 8, run-time inputs (e.g., run-time input 804) may be received from various sensors deployed within a monitored space.”); responsive to selection of the first spatial sector, [use the first machine-learning model to extract the first spatial sector audio data] (Naylor, for a first runtime input (first particular relative location/orientiation), use a first machine learning model: para. 0099 “In some implementations, speech processing process 11 may select 724 a speech processing model from the plurality of speech processing models using the one or more run-time inputs. For example, speech processing process 11 may select a particular speech processing model from the plurality of trained speech processing models in response to receiving a particular run-time input or set of run-time inputs corresponding to inputs used to train the speech processing model. …”); and responsive to selection of the second spatial sector, [use the second machine-learning model to extract the spatial sector audio data] (Naylor, for a second runtime input (second particular relative location/orientiation), use a second machine learning model: para. 0099 “In some implementations, speech processing process 11 may select 724 a speech processing model from the plurality of speech processing models using the one or more run-time inputs. For example, speech processing process 11 may select a particular speech processing model from the plurality of trained speech processing models in response to receiving a particular run-time input or set of run-time inputs corresponding to inputs used to train the speech processing model. …”; para. 0096 “While an example is provided of receiving e.g., one speech signal, it will be appreciated that any number of speech signals may be received 720 within the scope of the present disclosure.”).
Cutler, Premont, and Naylor are considered to be analogous to the claimed invention as they are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler in view of Premont to incorporate the teachings of Naylor in order to select, based on sensor input, the first and second spatial sector; responsive to selection of the first spatial sector, using the first machine learning model to generate the first spatial sector audio data; and responsive to selection of the second spatial sector, using the second machine learning model to generate the second spatial sector audio data. Doing so would be beneficial, as this would provide a number of machine learning models which can be selected from for processing the audio signals, allowing for specific models which have been trained on the same or similar input to be utilized at run-time (Naylor, para. 0098-0099).
6. Claims 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Cutler in view of Naylor, and further in view of Nakagawa et al. (US 12,444,431 B1, hereinafter Nakagawa).
Regarding claim 9, Cutler in view of Premont does not specifically disclose based on sensor input indicating that a first sound source is detected in the first spatial sector and a second sound source is detected in the second spatial sector.
Naylor teaches based on sensor input indicating that a first sound source is detected in the first spatial sector and a second sound source is detected in the second spatial sector (Naylor, para. 0095 “In some implementations, speech processing process 11 may receive 718 one or more run-time inputs indicative of at least one of: a relative location of the speaker and the microphone array, and a relative orientation of the speaker and the microphone array. As discussed above and referring again to the example of FIG. 8, run-time inputs (e.g., run-time input 804) may be received from various sensors deployed within a monitored space.”; Naylor further teaches multiple (e.g. two) sound sources (e.g. speakers); para. 0035 “As shown in the example of FIG. 3, microphone array 300 may be configured to receive one or more speech signals (e.g., speech signal 308) from one or more speakers (e.g., speaker 310).”).
Cutler, Premont, and Naylor are considered to be analogous to the claimed invention as they are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler in view of Premont to incorporate the teachings of Naylor in order to make a decision based on sensor input indicating that a first sound source is detected in the first spatial sector and a second sound source is detected in the second spatial sector. Doing so would be beneficial, given the same rationale as claim 7.
Cutler in view of Premont and Naylor does not specifically disclose [based on sensor input…] perform noise suppression on the first spatial sector audio data based on the second spatial sector audio data to generate the output data.
Nakagawa teaches to perform noise suppression on the first spatial sector audio data based on the second spatial sector audio data to generate the output data (Fig. 9B, first spatial sector audio data (Microphones 112a, z1(n)) is noise suppressed (via AEC 920) via second spatial sector audio data (Microphones 112b, z2(n)) to generate output data (970); Col. 24 Lines 54-61 “For example, the AEC component 920 may select a first channel of the first microphone audio signals (e.g., Z.sub.1a(n, k)) corresponding to the first rear-facing microphone 802 as a first reference signal, may select a first channel of the second microphone audio signals (e.g., Z.sub.2a(n, k)) corresponding to the first front-facing microphone 806 as a first target signal, and perform AIC processing 980 to remove the first reference signal from the first target signal.”).
Cutler, Premont, Naylor, and Nakagawa are considered to be analogous to the claimed invention as they are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler in view of Premont and Naylor to incorporate the teachings of Nakagawa in order to perform noise suppression on the first spatial sector audio data based on the second spatial sector audio data to generate the output data. Doing so would be beneficial, as this would attenuate/remove echo signals captured in an input audio signal which may have otherwise reduced speech quality (Nakagawa, Col. 22, Lines 4-18).
Regarding claim 10, Cutler in view of Premont, Naylor and Nakagawa teaches obtain, from the first spatial sector audio data (Nakagawa: Fig. 9B, signals z2(n) from microphones 112b), first spatial sector first subband audio data and first spatial sector second subband audio data (Fig. 9B, “Subband Analysis 910” creates subband domain signal Z2(n,k) comprising at least a first and second subband: Col. 8 Lines 61-67 and Col. 9 Lines 1-11 “In some examples, the device 110 may convert microphone audio data z(t) 210 from the time-domain to the subband-domain. For example, the device 110 may use a plurality of bandpass filters to generate microphone audio data z(t, k) in the subband-domain, with an individual bandpass filter centered on a narrow frequency range. Thus, a first bandpass filter may output a first portion of the microphone audio data z(t) 210 as a first time-domain signal associated with a first subband (e.g., first frequency range), a second bandpass filter may output a second portion of the microphone audio data z(t) 210 as a time-domain signal associated with a second subband (e.g., second frequency range), and so on, such that the microphone audio data z(t, k) comprises a plurality of individual subband signals (e.g., subbands). As used herein, a variable z(t, k) corresponds to the subband-domain signal and identifies an individual sample associated with a particular time t and tone index k.”); obtain, from the second spatial sector audio data (Fig. 9B, signals z1(n) from microphones 112a), second spatial sector first subband audio data and second spatial sector second subband audio data (Fig. 9B, “Subband Analysis 910” creates subband domain signal Z1(n,k) comprising at least a first and second subband (see Col. 8 Lines 61-67 and Col. 9 Lines 1-11, as cited above)); perform noise suppression on the first spatial sector first subband audio data (perform noise suppression on Z2(n,k), which contains the first subband for the first spatial sector, by inputting to AEC 920) based on second spatial sector first subband audio data (AEC 920 performed based on reference signal Z1(n,k), which contains the first subband for the second spatial sector: Col. 24 Lines 54-61 “For example, the AEC component 920 may select a first channel of the first microphone audio signals (e.g., Z.sub.1a(n, k)) corresponding to the first rear-facing microphone 802 as a first reference signal…”) to generate first subband noise suppressed audio data (isolated audio Z’2(n,k), which contains the noise suppressed first subband of the first spatial sector, is generated; Col. 24 Lines 54-61 “For example, the AEC component 920 may select a first channel of the first microphone audio signals (e.g., Z.sub.1a(n, k)) corresponding to the first rear-facing microphone 802 as a first reference signal, may select a first channel of the second microphone audio signals (e.g., Z.sub.2a(n, k)) corresponding to the first front-facing microphone 806 as a first target signal, and perform AIC processing 980 to remove the first reference signal from the first target signal.”; Col. 24 Lines 17-21 “Similarly, the AEC component 920 may perform second adaptive filtering to the second microphone audio signals Z.sub.2(n, k) using the first microphone audio signals Z.sub.1(n, k) as the reference 924 to generate the second isolated audio signals Z′.sub.2(n, k).”); perform noise suppression on the first spatial sector second subband audio data (perform noise suppression on Z2(n,k), which contains the second subband for the first spatial sector, by inputting to AEC 920) based on second spatial sector second subband audio data (AEC 920 performed based on reference signal Z1(n,k), which contains the second subband for the second spatial sector: Col. 24 Lines 54-61 “For example, the AEC component 920 may select a first channel of the first microphone audio signals (e.g., Z.sub.1a(n, k)) corresponding to the first rear-facing microphone 802 as a first reference signal…”) to generate second subband noise suppressed audio data (isolated audio Z’2(n,k), which contains the noise suppressed second subband of the first spatial sector, is generated; Col. 24 Lines 54-61 “For example, the AEC component 920 may select a first channel of the first microphone audio signals (e.g., Z.sub.1a(n, k)) corresponding to the first rear-facing microphone 802 as a first reference signal, may select a first channel of the second microphone audio signals (e.g., Z.sub.2a(n, k)) corresponding to the first front-facing microphone 806 as a first target signal, and perform AIC processing 980 to remove the first reference signal from the first target signal.”; Col. 24 Lines 17-21 “Similarly, the AEC component 920 may perform second adaptive filtering to the second microphone audio signals Z.sub.2(n, k) using the first microphone audio signals Z.sub.1(n, k) as the reference 924 to generate the second isolated audio signals Z′.sub.2(n, k).”); generate the output based on the first subband noise suppressed audio data and the second subband noise suppressed audio data (Fig. 9B, Z’2(n,k), which contains the first and second noise-suppressed subband audio data, used to generate subband domain output M(n,k) corresponding to output time domain audio signal m(n)).
Cutler, Premont, Naylor, and Nakagawa are considered to be analogous to the claimed invention as they are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler in view of Premont and Naylor to incorporate the teachings of Nakagawa in order to obtain, from the first spatial sector audio data, first spatial sector first subband audio data and first spatial sector second subband audio data; obtain, from the second spatial sector audio data, second spatial sector first subband audio data and second spatial sector second subband audio data; perform noise suppression on the first spatial sector first subband audio data based on second spatial sector first subband audio data to generate first subband noise suppressed audio data; perform noise suppression on the first spatial sector second subband audio data based on second spatial sector second subband audio data to generate second subband noise suppressed audio data; and generate the output data based on the first subband noise suppressed audio data and the second subband noise suppressed audio data. Doing so would be beneficial given the same rationale as claim 9.
7. Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Cutler in view of Premont, and further in view of Sharma & Naylor (US 2021/0350815 A1, hereinafter Sharma).
Regarding claim 12, Cutler in view of Premont discloses the microphone array (see above claim mapping). However, Cutler in view of Premont does not specifically disclose wherein a first subset of the microphone array is configured to generate the first audio data, and wherein a second subset of the microphone array is configured to generate the second audio data.
Sharma teaches wherein a first subset of the microphone array is configured to generate the first audio data, and wherein a second subset of the microphone array is configured to generate the second audio data. (para. 0052 “Accordingly, modular ACD system 54 and/or audio recording system 104 may be configured to utilize one or more of the discrete audio acquisition devices (e.g., audio acquisition devices 202, 204, 206, 208, 210, 212, 214, 216, 218) to form an audio recording beam. For example, modular ACD system 54 and/or audio recording system 104 may be configured to utilize audio acquisition device 210 to form audio recording beam 220, thus enabling the capturing of audio (e.g., speech) produced by encounter participant 226 (as audio acquisition device 210 is pointed to (i.e., directed toward) encounter participant 226). Additionally, modular ACD system 54 and/or audio recording system 104 may be configured to utilize audio acquisition devices 204, 206 to form audio recording beam 222, thus enabling the capturing of audio (e.g., speech) produced by encounter participant 228 (as audio acquisition devices 204, 206 are pointed to (i.e., directed toward) encounter participant 228). Additionally, modular ACD system 54 and/or audio recording system 104 may be configured to utilize audio acquisition devices 212, 214 to form audio recording beam 224, thus enabling the capturing of audio (e.g., speech) produced by encounter participant 230 (as audio acquisition devices 212, 214 are pointed to (i.e., directed toward) encounter participant 230). Further, modular ACD system 54 and/or audio recording system 104 may be configured to utilize null-steering precoding to cancel interference between speakers and/or noise.”)
Cutler, Premont, and Sharma are considered to be analogous to the claimed invention as they both are in the same field of speech processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Cutler in view of Premont to incorporate the teachings of Sharma in order to specifically have a first subset of the microphone array be configured to generate the first audio data, and have a second subset of the microphone array be configured to generate the second audio data. Doing so would enable both having separate recording beams for multiple sources of desired audio (e.g. speech), while also allowing for null-steering precoding to cancel interference between speakers and/or noise (Sharma, para. 0052).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Togami et al. (US 2024/0007817 A1): apply ML model for a left channel and for a right channel of audio (Fig. 6), perform audio enhancement using a first ML model and a second different ML model (Fig. 7)
Law et al. (US 2023/0379648 A1): utilize a plurality of machine learning models to process audio data objects (Fig. 4)
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CODY DOUGLAS HUTCHESON whose telephone number is (703)756-1601. The examiner can normally be reached M-F 8:00AM-5:00PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pierre-Louis Desir can be reached at (571)-272-7799. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CODY DOUGLAS HUTCHESON/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
