DETAILED ACTION
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01 May 2026 has been entered.
Response to Amendment
The amendment filed 01 May 2026 has been accepted and considered in this office action. Claims 1, 13, and 20 have been amended.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 13, and 20 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 § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1-4, 8-10, 13-16, and 20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Fenghai et al. (CN 114,566,179) in view of Lollmann et al. (Uniform and warped low delay filter-banks for speech enhancement).
NOTE: Page numbers in citations will refer to the translation provided by applicant 07 August 2024.
Consider claim 1, Fenghai teaches A device (abstract and figure 1) comprising:
one or more processors (page 23, n0152, processor) configured to:
obtain audio data representing one or more audio signals, the audio data including a first segment and a second segment subsequent to the first segment (page 7, n0028-29, also page 9, n0043-44, incoming noisy speech signals, divided into frames, i.e. segments);
perform one or more transform operations on the first segment to generate frequency-domain audio data (page 7, n0030, also page 9, n0044, performing time-frequency domain transformation);
provide input data based on the frequency-domain audio data as input to one or more machine-learning models to generate a noise-suppression output (page 10, n0049-51, determining gain function, n0056-65, using deep learning to determine gain functions);
perform one or more reverse transform operations on the noise-suppression output to generate time-domain filter coefficients (page 10, n0052, determining time domain filter corresponding to frequency gain function G,); and
perform time-domain filtering of the second segment using the time-domain filter coefficients to generate a noise-suppressed output signal (page 10, n0053, perform time domain filtering to generated enhanced speech).
Fenghai does not specifically teach wherein generation of the time-domain filter coefficients is independent of the second segment.
In the same field of time domain filtering signals, Lollmann teaches wherein generation of the time-domain filter coefficients is independent of the second segment (section 3.3, and figure 5, time mismatch of τ samples may be eliminated by using a delay of length τ. However the delay is optional and Lollmann states that it may be less problematic to eliminate the delay and filter with the time mismatch.).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to filter the audio signal with coefficients generated by a previous portion of the audio signal as taught by Lollmann in the system of Fenghai in order to further reduce delay in live filtering operations (Lollmann section 3.3.)
Consider claim 2, Fenghai teaches the device of claim 1, wherein the input data includes the frequency-domain audio data (page 10, n0049-51, determining gain function from frequency spectrum, n0056-65, using deep learning to determine gain functions).
Consider claim 3, Fenghai teaches the device of claim 1, wherein the one or more machine-learning models are configured to generate output including a frequency mask representing an estimated magnitude of noise in the frequency-domain audio data for each frequency bin of a plurality of frequency bins, and wherein the noise-suppression output includes the frequency mask (page 10, n0049-51, determining gain function based on the noise magnitude at each frequency point, n0056-65, using deep learning to determine gain function, which is represents a frequency mask, or filter).
Consider claim 4, Fenghai teaches the device of claim 1, wherein the one or more machine-learning models are configured to generate output including noise-suppressed audio data, wherein the one or more processors are configured to determine, based on the noise-suppressed audio data, a frequency mask representing an estimated magnitude of noise in the frequency-domain audio data for each frequency bin of a plurality of frequency bins, and wherein the noise-suppression output includes the frequency mask (page 10, n0049-51, determining gain function based on the noise magnitude at each frequency point, n0056-65, using deep learning to determine gain function, which is represents a frequency mask, or filter, 0054, estimating pure speech as well. 0065, gain function based on clean speech and noise ratios).
Consider claim 8, Fenghai teaches The device of claim 1, wherein the time-domain filter coefficients include linear phase finite impulse response (FIR) filter coefficients, minimum phase FIR filter coefficients, autoregressive filter coefficients, infinite impulse response (IIR) filter coefficients, or all-pole filter coefficients (page 13-14, n0081-90, converting the gain function to an FIR time domain filter).
Consider claim 9, Fenghai teaches The device of claim 1, wherein the one or more processors are integrated into a wearable device (page 1, n0002, hearing aids).
Consider claim 10, Fenghai teaches The device of claim 1, further comprising one or more microphones, wherein the one or more audio signals are received from the one or more microphones (page 7, n0028, receiving signal from microphone).
Consider claim 13, Fenghai teaches A method (abstract and figure 1) comprising:
obtaining audio data representing one or more audio signals, the audio data including a first segment and a second segment subsequent to the first segment (page 7, n0028-29, also page 9, n0043-44, incoming noisy speech signals, divided into frames, i.e. segments);
performing one or more transform operations on the first segment to generate frequency-domain audio data (page 7, n0030, also page 9, n0044, performing time-frequency domain transformation);
providing input data based on the frequency-domain audio data as input to one or more machine-learning models to generate a noise-suppression output (page 10, n0049-51, determining gain function, n0056-65, using deep learning to determine gain functions);
performing one or more reverse transform operations on the noise-suppression output to generate time-domain filter coefficients (page 10, n0052, determining time domain filter corresponding to frequency gain function G,); and
performing time-domain filtering of the second segment using the time-domain filter coefficients to generate a noise-suppressed output signal (page 10, n0053, perform time domain filtering to generated enhanced speech).
Fenghai does not specifically teach wherein generation of the time-domain filter coefficients is independent of the second segment.
In the same field of time domain filtering signals, Lollmann teaches wherein generation of the time-domain filter coefficients is independent of the second segment (section 3.3, and figure 5, time mismatch of τ samples may be eliminated by using a delay of length τ. However the delay is optional and Lollmann states that it may be less problematic to eliminate the delay and filter with the time mismatch.).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to filter the audio signal with coefficients generated by a previous portion of the audio signal as taught by Lollmann in the system of Fenghai in order to further reduce delay in live filtering operations (Lollmann section 3.3.)
Claim 14 contains similar limitations as claim 2 and is therefore rejected for the same reasons.
Claim 15 contains similar limitations as claim 3 and is therefore rejected for the same reasons.
Claim 16 contains similar limitations as claim 4 and is therefore rejected for the same reasons.
Consider claim 20, Fenghai teaches A non-transitory computer-readable medium storing instructions that are executable by one or more processors (page 23, n0152, RAM, ROM, processors) to cause the one or more processors to:
obtaining audio data representing one or more audio signals, the audio data including a first segment and a second segment subsequent to the first segment (page 7, n0028-29, also page 9, n0043-44, incoming noisy speech signals, divided into frames, i.e. segments);
performing one or more transform operations on the first segment to generate frequency-domain audio data (page 7, n0030, also page 9, n0044, performing time-frequency domain transformation);
providing input data based on the frequency-domain audio data as input to one or more machine-learning models to generate a noise-suppression output (page 10, n0049-51, determining gain function, n0056-65, using deep learning to determine gain functions);
performing one or more reverse transform operations on the noise-suppression output to generate time-domain filter coefficients (page 10, n0052, determining time domain filter corresponding to frequency gain function G,); and
performing time-domain filtering of the second segment using the time-domain filter coefficients to generate a noise-suppressed output signal (page 10, n0053, perform time domain filtering to generated enhanced speech).
Fenghai does not specifically teach wherein generation of the time-domain filter coefficients is independent of the second segment.
In the same field of time domain filtering signals, Lollmann teaches wherein generation of the time-domain filter coefficients is independent of the second segment (section 3.3, and figure 5, time mismatch of τ samples may be eliminated by using a delay of length τ. However the delay is optional and Lollmann states that it may be less problematic to eliminate the delay and filter with the time mismatch.).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to filter the audio signal with coefficients generated by a previous portion of the audio signal as taught by Lollmann in the system of Fenghai in order to further reduce delay in live filtering operations (Lollmann section 3.3.)
Claim(s) 5, 7, 17, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Fenghai and Lollmann as applied to claims 1 and 13 above, and further in view of Huang et al. (US PAP 2021/0125625).
Consider claim 5, Fenghai and Lollmann teach he device of claim 1, but do not specifically teach to generate the noise-suppression output, the one or more processors are configured to perform beamforming operations on the frequency-domain audio data to determine beamformed audio data distinguishing a portion of the audio data from a target audio source and a portion of the audio data from a non-target audio source, wherein the input data includes the beamformed audio data.
In the same field of noise suppression, Huang teaches to generate the noise-suppression output, the one or more processors are configured to perform beamforming operations on the frequency-domain audio data to determine beamformed audio data distinguishing a portion of the audio data from a target audio source and a portion of the audio data from a non-target audio source, wherein the input data includes the beamformed audio data (figure 1, and paragraphs 0020-27, performing beamforming in the frequency domain, and at 0026, separating noise from speech).
Therefore it would have been obvious to one of ordinary skill in the art at the time of effective filing to use beamforming as taught by Huang in the system of Fenghai and Lollmann in order to determine better estimates of noise, and avoiding canceling desired signals, see Huang 0026.
Consider claim 7, Fenghai and Lollmann teach The device of claim 1, but do not specifically teach to process the frequency-domain audio data to generate the noise-suppression output, the one or more processors are configured to perform source separation operations to determine source-separated audio data, wherein the input data includes the source-separated audio data.
In the same field of noise suppression, Huang teaches to process the frequency-domain audio data to generate the noise-suppression output, the one or more processors are configured to perform source separation operations to determine source-separated audio data, wherein the input data includes the source-separated audio data (figure 1, and paragraphs 0020-27, performing beamforming in the frequency domain, and at 0026, separating noise from speech).
Therefore it would have been obvious to one of ordinary skill in the art at the time of effective filing to use beamforming as taught by Huang in the system of Fenghai and Lollmann in order to determine better estimates of noise, and avoiding canceling desired signals, see Huang 0026.
Claim 17 contains similar limitations as claim 5 and is therefore rejected for the same reasons.
Claim 19 contains similar limitations as claim 7 and is therefore rejected for the same reasons.
Claim(s) 6 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Fenghai and Lollmann as applied to claims 1 and 13 above, and further in view of Lou et al. (US PAP 2016/0240210).
Consider claim 6, Fenghai and Lollmann teach The device of claim 1, but do not specifically teach to process the frequency-domain audio data to generate the noise-suppression output, the one or more processors are configured to perform speech augmentation operations to determine speech-augmented audio data, wherein the input data includes the speech-augmented audio data.
In the same field of noise suppression, Lou teaches to process the frequency-domain audio data to generate the noise-suppression output, the one or more processors are configured to perform speech augmentation operations to determine speech-augmented audio data, wherein the input data includes the speech-augmented audio data (0059, formant emphasis filter can be used to emphasize speech portions of the signal before further processing).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to use speech emphasis filters as taught by Lou in the system of Fenghai and Lollmann in order to improve the performance of downstream speech processing (Lou 0059).
Claim 18 contains similar limitations as claim 6 and is therefore rejected for the same reasons.
Claim(s) 11 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Fenghai and Lollmann as applied to claim 1 and further in view of in view of Ganeshkumar (US PAP 2022/0060812).
Consider claim 11, Fenghai and Lollmann teach the device of claim 10, but do not specifically teach an adaptive noise cancellation filter coupled to at least one of the one or more microphones.
In the same field of speech processing, Ganeshkumar teaches an adaptive noise cancellation filter coupled to at least one of the one or more microphones (0060, using an adaptive filter to cancel known signals from the speaker).
Therefore it would have been obvious to one of ordinary skill in the art at the time of effective filing to use adaptive filters as taught by Ganeshkumar in the system of Fenghai and Lollmann in order to allow for better cancelation of known but unwanted audio signals (Ganeshkumar 0060).
Consider claim 12, Fenghai and Lollmann teach the device of claim 11, further comprising one or more speakers and one or more microphones coupled to the one or more processors and integrated into a wearable device (Fenghai page 1-2, n0002 hearing aids and headphones, using microphones. Speakers are also known to be part of both devices), but do not specifically teach wherein the one or more microphones include at least one external microphone configured to generate the audio data and at least one feedback microphone configured to generate a feedback signal based on sound produced by the one or more speakers responsive to the noise-suppressed output signal.
In the same field of speech processing, Ganeshkumar teaches wherein the one or more microphones include at least one external microphone configured to generate the audio data and at least one feedback microphone configured to generate a feedback signal based on sound produced by the one or more speakers responsive to the noise-suppressed output signal (figure 1, external microphones 24A and B, internal microphones 18A and B, near speakers 28A and B. 0039, internal microphones may be feedback microphones, claim 2 feedback cancelation).
Therefore it would have been obvious to one of ordinary skill in the art at the time of effective filing to use internal and external mics as taught by Ganeshkumar in the system of Fenghai and Lollmann in order to allow for better cancelation of feedback.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOUGLAS C GODBOLD whose telephone number is (571)270-1451. The examiner can normally be reached 6:30am-5pm Monday-Thursday.
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, Andrew Flanders can be reached at (571)272-7516. 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.
DOUGLAS GODBOLD
Examiner
Art Unit 2655
/DOUGLAS GODBOLD/Primary Examiner, Art Unit 2655
Prosecution Insights