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 .
DETAILED ACTION
Introduction
This action responds to the application 18,954,430 filed on 11-20-2024. Claims 1-26 are pending.
Claim Rejections - 35 USC § 112
3. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3-6 and 16-19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claims 3, and 16 are recited "determining, using a cleaner (230), based on the respective frequency-domain representations (218a) of the respective output audio signals, an estimate of the attenuated residual echo"
attempts to define the subject-matter in terms of the result to be achieved (estimating a residual echo), without stating the essential features to achieve the result claimed (how is the residual estimated?).
It should be noted that "cleaner" is not a commonly known term in the field of echo cancellation.
Claims 4, 17 It is not clear how the correlation of the two signals results in an estimation of the residual.
Claim Rejections - 35 USC § 102
4. 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 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.
5. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
6. Claims 1 and 14 are rejected under 35 U.S.C. 102a (1) as being anticipated by
ZHANG SHIMIN ET AL: "Multi-Task Deep Residual Echo Suppression with Echo-Aware Loss", ICASSP 2022 - 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 23 May 2022 (2022-05-23), pages 9127-9131, XP034158706, DOI: 10.1109/ICASSP43922.2022.9746733 [retrieved on 2022-04-27]
Consider Claim 1, Zhang teaches a computer-implemented method executed on data processing hardware that causes the data processing hardware to perform operations comprising: receiving a frequency-domain representation of an output audio signal output from a linear acoustic echo canceller (AEC and abstract), the output audio signal comprising target speech captured by an audio capture device of a user device and residual echo of reference audio output by an audio output device of the user device;
(see, Figure 1: E and page 9127-9128)
receiving a frequency-domain representation of the reference audio;
(see, Figure 1: X and page 9127-9128) determining, using a neural echo suppressor (NF I S, see fig. 2)), based on the frequency-domain representation of the output audio signal and the frequency-domain representation of the reference audio, a time-frequency mask; and
section 2.3: "In this paper, we explore three types of combinations, namely DX, EX and DEY mask calculation: Equation 2
processing, using the time-frequency mask, the frequency -domain representation of the output audio signal to attenuate the residual echo in an enhanced audio signal.
(see Equation 3, figure 1: E and page 9129-9130)
The objections concerning claim 1 apply, mutatis mutandis, to claim 14.
7. Claims 1-26 are rejected under 35 U.S.C. 102a (1) as being anticipated by Wung et al. (US PAT. 10,074,380).
Consider Claim 1, Wung teaches a computer-implemented method executed on data processing hardware that causes the data processing hardware to perform operations (see fig. 8) comprising:
receiving (see fig. 2) a frequency-domain representation of an output audio signal output from a linear acoustic echo canceller (LAEC), the output audio signal comprising target speech captured by an audio capture device of a user device and residual echo of reference audio output by an audio output device of the user device(see figs. 2-5 and col. 3 line 12-col. 4, line 67);
receiving (see fig. 1) a frequency-domain representation of the reference audio; determining, using a neural echo suppressor (NES), based on the frequency-domain representation of the output audio signal(see figs. 2-5 and col. 5 line 8-col. 6, line 67); and
the frequency-domain representation of the reference audio, a time-frequency mask; and processing, using the time-frequency mask, the frequency-domain representation of the output audio signal to attenuate the residual echo in an enhanced audio signal(see figs. 2-8 and col. 7 line 1-col. 8, line 46).
Consider Claims 2 and 3, Wung teaches the computer-implemented method wherein the NES comprises one or more self-attention layers(see figs. 2-8 and col. 5 line 8-col. 6, line 67); and the computer-implemented method wherein the operations further comprise: for each respective additional audio capture device of a plurality of additional audio capture devices of the user device, receiving a respective frequency-domain representation of a respective output audio signal output from the LAEC for the respective additional audio capture device, the respective output audio signal comprising respective residual echo; and determining, using a cleaner, based on the respective frequency-domain representations of the respective output audio signals, an estimate of the attenuated residual echo (see figs. 2-8 and col. 7 line 1-col. 8, line 46).
Consider Claims 4 and 5, Wung teaches the computer-implemented method wherein determining the estimate of the attenuated residual echo comprises correlating a frequency-domain representation of the enhanced audio signal with each of the respective frequency-domain representations of the respective output audio signals(see figs. 2-8 and col. 5 line 8-col. 6, line 67); and the computer-implemented method wherein: the cleaner comprises a plurality of coefficients; and the operations further comprise training the plurality of coefficients using a minimum mean square error criterion(see figs. 2-8 and col. 5 line 8-col. 6, line 67).
Consider Claims 6 and 7, Wung teaches the computer-implemented method wherein: the cleaner comprises a plurality of coefficients; and the operations further comprise training the plurality of coefficients: when target speech is not present; or prior to detection of a keyword in target speech(see figs. 2-8 and col. 5 line 8-col. 6, line 67); and the computer-implemented method wherein :the frequency-domain representation of the output audio signal comprises a plurality of log-compressed magnitudes for respective ones of a plurality of frequency sub-bands; and the frequency-domain representation of the reference audio comprises a plurality of log-compressed magnitudes for respective ones of the plurality of frequency sub- bands(see figs. 2-5 and col. 5 line 8-col. 6, line 67).
Consider Claims 8 and 9, Wung teaches the computer-implemented method wherein the operations further comprise, for each training step of a plurality of training steps: generating target audio training data comprising sampled speech of interest and a version of an interfering signal; processing, using the LAEC, the target audio training data and the interfering signal to generate predicted enhanced audio data, the LAEC configured to attenuate the interfering signal in the predicted enhanced audio data; processing, using the NES, the predicted enhanced audio data to generate predicted further enhanced audio data, the NES configured to suppress the interfering signal in the predicted further enhanced audio data; and training coefficients of the NES based on a loss term computed based on the predicted further enhanced audio data and the sampled speech of interest(see figs. 2-5 and col. 3 line 12-col. 4, line 67);.
9. The computer-implemented method of claim 8, wherein processing, using the LAEC, the target audio training data and the interfering signal to generate the predicted enhanced audio data comprises using, for each training step, randomly sampled LAEC parameters (see figs. 2-5 and col. 3 line 12-col. 4, line 67).
Consider Claims 10 and 11, Wung teaches the computer-implemented method wherein at least a portion of the randomly sampled LAEC parameters reduce a performance of the LAEC(see figs. 2-5 and col. 3 line 12-col. 4, line 67); and the computer-implemented method wherein the loss term comprises at least one of a time-domain scale-invariant signal-to-noise ratio, an automatic speech recognition encoder loss, or a masking loss(see figs. 2-5 and col. 3 line 12-col. 4, line 67).
Consider Claims 12 and 13, Wung teaches the computer-implemented method wherein the LAEC is configured to perform echo cancellation based on a frequency-domain representation of the target speech and a frequency-domain representation of the reference audio(see figs. 2-5 and col. 3 line 12-col. 4, line 67); and the computer-implemented method wherein: the LAEC is configured to perform echo cancellation based on a first set of frequency-domain sub-bands; and the NES is configured to determine the time-frequency mask based on a second set of frequency-domain sub-bands different from the first set of frequency-domain sub- bands(see figs. 2-5 and col. 3 line 12-col. 4, line 67).
Consider Claim 14, Wung teaches a system, comprising: data processing hardware; and memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations (see fig. 8 col.8, line 46-col. 9, line 46)comprising:
receiving (see fig. 2) a frequency-domain representation of an output audio signal output from a linear acoustic echo canceller (LAEC), the output audio signal comprising target speech captured by an audio capture device of a user device and residual echo of reference audio output by an audio output device of the user device(see figs. 2-5 and col. 3 line 12-col. 4, line 67);
receiving (see fig. 1) a frequency-domain representation of the reference audio; determining, using a neural echo suppressor (NES), based on the frequency-domain representation of the output audio signal(see figs. 2-5 and col. 5 line 8-col. 6, line 67); and
the frequency-domain representation of the reference audio, a time-frequency mask; and processing, using the time-frequency mask, the frequency-domain representation of the output audio signal to attenuate the residual echo in an enhanced audio signal(see figs. 2-8 and col. 7 line 1-col. 8, line 46).
Consider Claims 15 and 16, Wung teaches the system wherein the NES comprises one or more self-attention layers(see figs. 2-8 and col. 5 line 8-col. 6, line 67); and the system wherein the operations further comprise: for each respective additional audio capture device of a plurality of additional audio capture devices of the user device, receiving a respective frequency-domain representation of a respective output audio signal output from the LAEC for there spective additional audio capture device, the respective output audio signal comprising respective residual echo; and determining, using a cleaner, based on the respective frequency-domain representations of the respective output audio signals, an estimate of the attenuated residual echo(see figs. 2-8 and col. 7 line 1-col. 8, line 46).
Consider Claims 17 and 18, Wung teaches the system wherein determining the estimate of the attenuated residual echo comprises correlating a frequency-domain representation of the enhanced audio signal with each of the respective frequency-domain representations of the respective output audio signals(see figs. 2-8 and col. 5 line 8-col. 6, line 67); and the system wherein: the cleaner comprises a plurality of coefficients; and the operations further comprise training the plurality of coefficients using a minimum mean square error criterion(see figs. 2-8 and col. 5 line 8-col. 6, line 67)..
Consider Claims 19 and 20, Wung teaches the system wherein: the cleaner comprises a plurality of coefficients; and the operations further comprise training the plurality of coefficients: when target speech is not present; or prior to detection of a keyword in target speech(see figs. 2-8 and col. 3 line 12-col. 4, line 67); and the system wherein: the frequency-domain representation of the output audio signal comprises a plurality of log-compressed magnitudes for respective ones of a plurality of frequency sub-bands; and the frequency-domain representation of the reference audio comprises a plurality of log-compressed magnitudes for respective ones of the plurality of frequency sub- bands(see figs. 2-5 and col. 3 line 12-col. 4, line 67).
Consider Claims 21 and 22, Wung teaches the system wherein the operations further comprise, for each training step of a plurality of training steps: generating target audio training data comprising sampled speech of interest and a version of an interfering signal; processing, using the LAEC, the target audio training data and the interfering signal to generate predicted enhanced audio data, the LAEC configured to attenuate the interfering signal in the predicted enhanced audio data; processing, using the NES, the predicted enhanced audio data to generate predicted further enhanced audio data, the NES configured to suppress the interfering signal in the predicted further enhanced audio data; and training coefficients of the NES based on a loss term computed based on the predicted further enhanced audio data and the sampled speech of interest(see figs. 2-8 and col. 3 line 12-col. 4, line 67); 22. The system of claim 21, wherein processing, using the LAEC, the target audio training data and the interfering signal to generate the predicted enhanced audio data comprises using, for each training step, randomly sampled LAEC parameters(see figs. 2-5 and col. 3 line 12-col. 4, line 67).
Consider Claims 23 and 24, Wung teaches the system wherein at least a portion of the randomly sampled LAEC parameters reduce a performance of the LAEC(see figs. 2-5 and col. 3 line 12-col. 4, line 67); and the system wherein the loss term comprises at least one of a time- domain scale-invariant signal-to-noise ratio, an automatic speech recognition encoder loss, or a masking loss(see figs. 2-5 and col. 3 line 12-col. 4, line 67).
Consider Claims 25 and 26, Wung teaches the system wherein the LAEC is configured to perform echo cancellation based on a frequency-domain representation of the target speech and a frequency-domain representation of the reference audio(see figs. 2-5 and col. 3 line 12-col. 4, line 67); and the system wherein: the LAEC is configured to perform echo cancellation based on a first set of frequency-domain sub-bands; and the NES is configured to determine the time-frequency mask based on a second set of frequency domain sub-bands different from the first set of frequency-domain sub-bands(see figs.2-5 and col. 3 line 12-col. 4, line 67).
Claim Rejections - 35 USC § 103
8. 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 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.
9. 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.
10. The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
11. Claims 2-13, 15-26 are rejected under 35 U.S.C. 103(a) as being unpatentable over ZHANG SHIMIN ET AL: "Multi-Task Deep Residual Echo Suppression with Echo-Aware Loss", ICASSP 2022 - 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 23 May 2022 (2022-05-23), pages 9127-9131, XP034158706, DOI: 10.1109/ICASSP43922.2022.9746733 [retrieved on 2022-04-27] in view of Defraene et al. (US 2019/0122685).
Consider claims 2-13, 15-26 do not appear to contain any additional features which, in combination with the features of any claim to which they refer, meet the requirements of the PCT with respect to novelty and/or inventive step. Claim 2 (claim 15): (Self-)Attention is an implementation detail of the neural network and not inventive.
However, Defraene teaches an implementation detail of the neural network(see figs. 2-6 and paragraphs[0046]- [0051]).
Therefore, it would have obvious to one of ordinary skill in the art before the effective filling date the invention was made to combine the teaching of Defraene in to the teaching of Zhang to provide a signal processor for performing signal enhancement, the signal processor comprising: an input-terminal, configured to receive an input-signaling; an output-terminal; an interference-cancellation-block configured to receive the input-signaling and to provide an interference-estimate-signaling and an interference-cancelled-signal based on the input-signaling. The signal processor further comprises a feature-block configured to provide a combination-feature-signal based on the interference-cancelled-signal and the interference-estimate-signaling; and a neural-network-block configured to apply model parameters to the combination-feature-signal to provide a neural-network-output-signal to the output-terminal.
Claims 3, 4, 16 and 17, Zhang as modified by Defraene discloses estimation of residual echo by the neural residual echo remover to obtain Z(k,t) (i.e. the difference between input signal and residual) (D1, Figure 1).
Consider claims 5, 8-11, 18 and 21-24, Zhang discloses the training features of claims 5, 8-11 (see, section 2.4).
Consider claims 6 and claim 19: Zhang as modified by Defraene discloses VAD (see, Figure 2d).
Consider claims 7 and 20, Zhang as modified by Defraene discloses frequency domain signals (see, Figure 1).
Consider claims 12, 13, 25 and 26: Zhang as modified by Defraene discloses standard AEC (see, Figure 1).
Conclusion
12. The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. Wung et al.(US PAT.10,546,593) are cited to show other related the ACOUSTIC ECHO CANCELLATION FOR DIGITAL ASSISTANTS USING NEURAL ECHO SUPPRESSION AND MULTI-MICROPHONE NOISE REDUCTION.
13. Any response to this action should be mailed to:
Mail Stop ____(explanation, e.g., Amendment or After-final, etc.)
Commissioner for Patents
P.O. Box 1450
Alexandria, VA 22313-1450
Facsimile responses should be faxed to:
(571) 273-8300
Hand-delivered responses should be brought to:
Customer Service Window
Randolph Building
401 Dulany Street
Alexandria, VA 22314
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to Lao,Lun-See whose telephone number is (571) 272-7501 The examiner
can normally be reached on Monday-Friday from 8:00 to 5:30.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's
supervisor, Nguyen Duc M(SPE), can be reached on (571) 272-7503.
Any inquiry of a general nature or relating to the status of this application or proceeding
should be directed to the Technology Center 2600 whose telephone number is (571) 272-2600.
/LUN-SEE LAO/Primary Examiner, Art Unit 2691 US Patent and Trademark Office
Knox
571-272-7501
Date 05-20-2026
Prosecution Insights