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 .
Response to Arguments
Applicant’s arguments with respect to claim(s) 1,3-4, 7-13, 15-17, 19-20, 23, 25-27 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.
A new search was made and art was found to Jing which teaches the claimed invention.
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.
Claim(s) 1-4, 8-13, 16-17, 20-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yang U.S. PAP 2025/0038726 A1, in view of Li U.S. Patent No. 9,741,360 B1 further in view of Jing U.S. PAP 2011/0026722.
Regarding claim 1 Yang teaches a method for audio signal processing in a device ( a method of performing content-aware audio processing for an audio signal, see par. [0007]), the method comprising:
receiving, at the device, an input audio signal, the audio signal comprising a speech component and a non-speech component (an audio input (audio input signal) 110 is provided first, see par. [0053]);
extracting the speech component (audio input 110 may be passed on for multi-object source separation in order to separate the audio 110 into one or more prominent audio objects/components which typically comprise those voice-related audio components, see par. [0054]) ;
modifying the speech component to generate a modified speech component (an audio analysis and classification step may be performed in order to further identify audio clusters of the audio and the separated objects, see par. [0055]; he voice extractor 220 may be configured to separate a voice component from an audio signal comprising the voice component and the residual component, see par. [0060]);
and mixing the modified speech component with at least a portion of the non-speech component to generate a synchronized playback audio signal(a dynamic gain (150) may be derived, in order to be applied to the remixing audio based on the corresponding cluster information as determined in block 130, see par. [0056]).
However Yang does not teach modifying the speech component to generate a modified speech component by applying a gain to an entirety of the speech component, wherein the gain is modified on at least one of a user input separate from the input audio signal or a user profile.
In the same field of endeavor Li teaches a method for digital speech signal enhancement using signal processing algorithms and acoustic models for target speakers. The invention further relates to speech enhancement using microphone array signal processing and speaker recognition. A hearing impaired human also suffers from the degradation of speech quality. Although a person with normal hearing can tolerate considerable noise and interferences in the captured speech signal, listener fatigue easily arises with exposure to low signal to noise ratio (SNR) speech, see col. 1 lines 6-25. Li teaches modifying the speech component to generate a modified speech component by applying a gain to an entirety of the speech component, wherein the gain is modified on at least one of a user input separate from the input audio signal or a user profile (In FIG. 5, two identical acoustic feature extractors, 506 and 508, extract acoustic features from audio components 500 and 502, respectively. A database 504 of speaker profile(s) stores speaker models characterizing the probability density distribution (pdf) of acoustic features from target speakers. By comparing the acoustic features extracted from acoustic feature extractor 506 and 508 and speaker profile(s), a speech mixer weight generator 510 generates two speech mixing weights, or two gains, for audio components 500 and 502 respectively, and modules 512 and 514 apply these two gains on audio components 500 and 502 accordingly., see col. 5 lines 3-21).
It would have been obvious to one of ordinary skill in the art to combine the Yang invention with the teachings of Li for the benefit of lessening listener fatigue with exposure to low SNR speech see col. 1, lines 21-25.
However Yang in view of Li does not teach extracting the speech component using a dynamic filter periodically adapted by a trained machine-learning model according to the input signal.
In the same field of endeavor Jing teaches an LPF should model the static response of the SSM signal, both in magnitude and phase response. Then the speech signal gets filtered by an adaptive filter (H) that models the dynamic response of the SSM signal when speech is present. The error residual drives the adaptation of the filter, and the adaptation only takes place when the AVAD detects speech, see par. [0110].
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li invention with the teachings of Jing for the benefit of improved denoising performance, see par. [0017].
Regarding claim 3 Yang teaches the method of claim 2, wherein the trained machine-learning model comprises at least one memory cache configured to store data associated with the extracting (each of these separated audio objects may be stored in a separate track for necessary further processing at a later time, see par. [0054]).
Regarding claim 4 Yang teaches the method of claim 2, wherein the trained machine-learning model comprises a deep learning model configured to predict a filter, the filter being configured to extract the speech component from the input audio signal (the source separation (or in some cases, the voice extraction) functionality may be achieved for example by using a deep neural network (DNN)-based methodology , see par. [0009]; dividing the audio signal into a sequence of windowed, (half-)overlapping blocks, converting the audio signal data to the frequency domain e.g., by using a filter bank, see par. [0084]).
Regarding claim 8 Yang teaches the method of claim 1, wherein the gain comprises a dynamic gain associated with a desired signal-to-noise ratio (SNR) of the synchronized playback audio signal (the determination of the dynamic audio gain may involve identifying whether the residual audio component relates to noise or not, see par. [0017]).
Regarding claim 9 Yang teaches the method of claim 8, wherein the desired SNR of the synchronized playback audio signal is based, at least in part, on a model of an intelligibility of the speech component given the input audio signal (wideband loudness measure of the audio signal being remixed using the voice-related audio component and the residual audio component by attenuating any noise component contained in the residual audio component when the audio signal is identified to relate to user generated content, see par. [0023]).
Regarding claim 10 Yang teaches the method of claim 1, wherein the mixing is based, at least in part, on at least one of a recommendation, a specification, or legislation for an environment that the device is located in (the noise contained therein may very likely be related to unwanted or undesirable background noise(environment) rather than intended background sound that may convey some information of the creator's intent. Thus, by attenuating such unwanted noise, undesirable boosting or pumping of the noise during the application of the dynamic audio gain on the audio signal remix that may be noticeable when applying conventional techniques can be avoided, see par. [0023]).
Regarding claim 11 Yang teaches the method of claim 1, wherein the speech component comprises at least a first portion of the speech component and a second portion of the speech component, wherein modifying the speech component to generate the modified speech component comprises applying a first gain to the first portion of the speech component and a second gain to the second portion of the speech component, and wherein the first gain is different than the second gain (hen an audio clip under consideration has three adjacent segments, namely: the first noise segment, the second speech over noise segment, and the third noise segment, the conventional dynamic processing may be configured to boost the level in the first and third noise segments while maintaining the level in the second segment, see par. [0048]).
Regarding claim 12 Yang teaches the method of claim 1, wherein the device comprises a wearable audio device ( a normal handheld device, see par. [0023]).
Regarding claim 13 Yang teaches a system (a method of performing content-aware audio processing for an audio signal, a corresponding apparatus, see par. [0007]), comprising:
a device (apparatus, see par. [0033]);
and one or more processors coupled to the device (an apparatus including a processor, see par. [0033]), the one or more processors configured to:
receive, at the device, an input audio signal, the input audio signal comprising a speech component and a non-speech component (an audio input (audio input signal) 110 is provided first, see par. [0053]);
extract a speech component (audio input 110 may be passed on for multi-object source separation in order to separate the audio 110 into one or more prominent audio objects/components which typically comprise those voice-related audio components, see par. [0054]);
modify the speech component to generate a modified speech component (an audio analysis and classification step may be performed in order to further identify audio clusters of the audio and the separated objects, see par. [0055]; he voice extractor 220 may be configured to separate a voice component from an audio signal comprising the voice component and the residual component, see par. [0060]);
and mix the modified speech component with at least a portion of the non-speech component to generate a synchronized playback audio signal (a dynamic gain (150) may be derived, in order to be applied to the remixing audio based on the corresponding cluster information as determined in block 130, see par. [0056]).
However Yang does not teach modifying the speech component to generate a modified speech component by applying a gain to an entirety of the speech component, wherein the gain is modified on at least one of a user input separate from the input audio signal or a user profile.
In the same field of endeavor Li teaches a method for digital speech signal enhancement using signal processing algorithms and acoustic models for target speakers. The invention further relates to speech enhancement using microphone array signal processing and speaker recognition. A hearing impaired human also suffers from the degradation of speech quality. Although a person with normal hearing can tolerate considerable noise and interferences in the captured speech signal, listener fatigue easily arises with exposure to low signal to noise ratio (SNR) speech, see col. 1 lines 6-25. Li teaches modifying the speech component to generate a modified speech component by applying a gain to an entirety of the speech component, wherein the gain is modified on at least one of a user input separate from the input audio signal or a user profile (In FIG. 5, two identical acoustic feature extractors, 506 and 508, extract acoustic features from audio components 500 and 502, respectively. A database 504 of speaker profile(s) stores speaker models characterizing the probability density distribution (pdf) of acoustic features from target speakers. By comparing the acoustic features extracted from acoustic feature extractor 506 and 508 and speaker profile(s), a speech mixer weight generator 510 generates two speech mixing weights, or two gains, for audio components 500 and 502 respectively, and modules 512 and 514 apply these two gains on audio components 500 and 502 accordingly., see col. 5 lines 3-21).
It would have been obvious to one of ordinary skill in the art to combine the Yang invention with the teachings of Li for the benefit of lessening listener fatigue with exposure to low SNR speech see col. 1, lines 21-25.
However Yang in view of Li does not teach extracting the speech component using a dynamic filter periodically adapted by a trained machine-learning model according to the input signal.
However Yang in view of Li does not teach extracting the speech component using a dynamic filter periodically adapted by a trained machine-learning model according to the input signal.
In the same field of endeavor Jing teaches an LPF should model the static response of the SSM signal, both in magnitude and phase response. Then the speech signal gets filtered by an adaptive filter (H) that models the dynamic response of the SSM signal when speech is present. The error residual drives the adaptation of the filter, and the adaptation only takes place when the AVAD detects speech, see par. [0110].
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li invention with the teachings of Jing for the benefit of improved denoising performance, see par. [0017].
Regarding claim 16 Yang teaches the system of claim 13, wherein the gain comprises a dynamic gain associated with a desired signal-to-noise ratio (SNR) of the synchronized playback audio signal (the determination of the dynamic audio gain may involve identifying whether the residual audio component relates to noise or not, see par. [0017]).
Regarding claim 17 Yang teaches a non-transitory computer-readable medium comprising computer-executable instructions that, when executed by one or more processors of a device, cause the device to perform a method for audio signal processing (a method of performing content-aware audio processing for an audio signal, a computer-readable storage media, see par. [0007]), the method comprising:
receiving, at the device, an input audio signal, the input audio signal comprising a speech component and a non-speech component (an audio input (audio input signal) 110 is provided first, see par. [0053]);
extracting the speech component (audio input 110 may be passed on for multi-object source separation in order to separate the audio 110 into one or more prominent audio objects/components which typically comprise those voice-related audio components, see par. [0054]);
modifying the speech component to generate a modified speech component (an audio analysis and classification step may be performed in order to further identify audio clusters of the audio and the separated objects, see par. [0055]; he voice extractor 220 may be configured to separate a voice component from an audio signal comprising the voice component and the residual component, see par. [0060]);
and mixing the modified speech component with at least a portion of the non-speech component to generate a synchronized playback audio signal (a dynamic gain (150) may be derived, in order to be applied to the remixing audio based on the corresponding cluster information as determined in block 130, see par. [0056]).
However Yang does not teach modifying the speech component to generate a modified speech component by applying a gain to an entirety of the speech component, wherein the gain is modified on at least one of a user input separate from the input audio signal or a user profile.
In the same field of endeavor Li teaches a method for digital speech signal enhancement using signal processing algorithms and acoustic models for target speakers. The invention further relates to speech enhancement using microphone array signal processing and speaker recognition. A hearing impaired human also suffers from the degradation of speech quality. Although a person with normal hearing can tolerate considerable noise and interferences in the captured speech signal, listener fatigue easily arises with exposure to low signal to noise ratio (SNR) speech, see col. 1 lines 6-25. Li teaches modifying the speech component to generate a modified speech component by applying a gain to an entirety of the speech component, wherein the gain is modified on at least one of a user input separate from the input audio signal or a user profile (In FIG. 5, two identical acoustic feature extractors, 506 and 508, extract acoustic features from audio components 500 and 502, respectively. A database 504 of speaker profile(s) stores speaker models characterizing the probability density distribution (pdf) of acoustic features from target speakers. By comparing the acoustic features extracted from acoustic feature extractor 506 and 508 and speaker profile(s), a speech mixer weight generator 510 generates two speech mixing weights, or two gains, for audio components 500 and 502 respectively, and modules 512 and 514 apply these two gains on audio components 500 and 502 accordingly., see col. 5 lines 3-21).
It would have been obvious to one of ordinary skill in the art to combine the Yang invention with the teachings of Li for the benefit of lessening listener fatigue with exposure to low SNR speech see col. 1, lines 21-25.
However Yang in view of Li does not teach extracting the speech component using a dynamic filter periodically adapted by a trained machine-learning model according to the input signal.
However Yang in view of Li does not teach extracting the speech component using a dynamic filter periodically adapted by a trained machine-learning model according to the input signal.
In the same field of endeavor Jing teaches an LPF should model the static response of the SSM signal, both in magnitude and phase response. Then the speech signal gets filtered by an adaptive filter (H) that models the dynamic response of the SSM signal when speech is present. The error residual drives the adaptation of the filter, and the adaptation only takes place when the AVAD detects speech, see par. [0110].
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li invention with the teachings of Jing for the benefit of improved denoising performance, see par. [0017].
Regarding claim 20 Yang teaches the non-transitory computer-readable medium of claim 17, wherein the gain comprises a dynamic gain associated with a desired signal-to-noise ratio (SNR) of the synchronized playback audio signal (the determination of the dynamic audio gain may involve identifying whether the residual audio component relates to noise or not, see par. [0017]).
Regarding claim 27 Li teaches the method of claim 1, wherein the user profile is based on at least two of a user control input, past user activity, or another machine-learning model (algorithm separates the recorded mixtures from a plurality of microphones into statistically independent audio components. For each audio component, at least one of a plurality of predefined target speaker models are used to evaluate its likelihood that it belongs to the target speakers, see col. 1 lines 62-66).
Claim(s) 7, 15 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yang. U.S. PAP 2025/0038726 A1, in view of Li U.S. Patent No. 9,741,360 B1, in view of Jing U.S. PAP 2011/0026722 A1 further in view of Rennies-Hochmuth U.S. PAP 2023/0087486 A1.
Regarding claim 7 Yang in view of Li in view of Jing does not teach the method of claim 1, wherein the gain comprises a fixed gain.
In the same field of endeavor Rennies teaches enabling an improved trade-off between (speech) intelligibility and maintaining the sound scenes, see par. [0020]. Rennies teaches lowering channels that do not primarily include speech: In multichannel audio signals that are mixed in such a way that one channel (typically the center) includes a large part of the speech information and the other channels (e.g. left/right) mainly include background noise, one technical solution consists in attenuating the non-speech channels by a fixed gain (e.g. by 6 dB) and in that way to improve the signal to noise ratio (e.g. sound retrieval system (SRS) dialog clarity or adapted downmix rules for surround decoder), see par. [0014].
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li in view of Jing invention with the teachings of Rennies for the benefit of improving signal to noise ratio, see par. [0014].
Regarding claim 15 Yang in view of Li in view of Jing does not teach the system of claim 13, wherein the gain comprises a fixed gain.
In the same field of endeavor Rennies teaches enabling an improved trade-off between (speech) intelligibility and maintaining the sound scenes, see par. [0020]. Rennies teaches lowering channels that do not primarily include speech: In multichannel audio signals that are mixed in such a way that one channel (typically the center) includes a large part of the speech information and the other channels (e.g. left/right) mainly include background noise, one technical solution consists in attenuating the non-speech channels by a fixed gain (e.g. by 6 dB) and in that way to improve the signal to noise ratio (e.g. sound retrieval system (SRS) dialog clarity or adapted downmix rules for surround decoder), see par. [0014].
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li in view of Jing invention with the teachings of Rennies for the benefit of improving signal to noise ratio, see par. [0014].
Regarding claim 19 Yang in view of Li in view of Jing does not teach the non-transitory computer-readable medium of claim 17, wherein the gain comprises a fixed gain.
In the same field of endeavor Rennies teaches enabling an improved trade-off between (speech) intelligibility and maintaining the sound scenes, see par. [0020]. Rennies teaches lowering channels that do not primarily include speech: In multichannel audio signals that are mixed in such a way that one channel (typically the center) includes a large part of the speech information and the other channels (e.g. left/right) mainly include background noise, one technical solution consists in attenuating the non-speech channels by a fixed gain (e.g. by 6 dB) and in that way to improve the signal to noise ratio (e.g. sound retrieval system (SRS) dialog clarity or adapted downmix rules for surround decoder), see par. [0014].
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li in view of Jing invention with the teachings of Rennies for the benefit of improving signal to noise ratio, see par. [0014].
Claim(s) 23, 25-26 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yang. U.S. PAP 2025/0038726 A1, in view of Li U.S. Patent No. 9,741,360 B1, in view of Jing U.S. PAP 2011/0026722A1further in view of Woodruff U.S. Patent No. 11,393,486 B1.
Regarding claim 23 Yang in view of Li in view of Jing does not teach the system of claim 13, wherein to mix the modified speech component with the at least a portion of the input audio signal to generate the synchronized playback audio signal, the one or more processors are configured to mix based, at least in part, on at least one of a recommendation, a specification, or legislation for an environment type that the device is located in.
In a similar field of endeavor Woodruff teaches a customized compressor for applying dynamic range control in an audio system that has an against-the-ear audio device (personal listening device.) Also referred to as a noise aware compressor, the compressor is customized or configured according to the particular acoustic ambient environment to improve the sound reproduced for the user of the device, see col. 1 lines 28-34.
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li in view of Jing invention with the teachings of Woodruff for the benefit of improve the sound reproduced for a user on a device according to the particular ambient environment, see col. 1 lines 28-34.
Regarding claim 25 Yang in view of Li in view of Jing does not teach the method of claim 1, wherein at least one of a loudness or a dynamic range of the modified speech component in the synchronized playback audio signal is based, at least in part, on an environment type that the device is located in.
Woodruff teaches the compression (dynamic range control) performed by the ASE filter 6 is customized as follows. The analyzer 8 determines signal to noise ratio, SNR, in the input audio signal (from the external microphone 3.) Here, the acoustic ambient environment (and hence the input audio signal) contains speech by a talker (who is not the user.) When determining that the SNR is above a threshold, the ASE filter 6 becomes configured to apply upward compression to the input audio signal, see col. 6 lines 5-32.
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li in view of Jing invention with the teachings of Woodruff for the benefit of improve the sound reproduced for a user on a device according to the particular ambient environment, see col. 1 lines 28-34.
Regarding claim 26 Yang in view of Li in view of Jing do not teach the method of claim 10, wherein the environment type is one of configured by another user input, preset, or determined by the device.
Woodruff teaches wherein the environment type is one of configured by another user input, preset, or determined by the device (The transfer function of the ASE filter 6 is variable, e.g., on a frame by frame basis where each frame may include for example 1-10 milliseconds of the microphone signal, and may be set by an ambient sound environment analyzer 8, see col. 5 lines 17-29).
It would have been obvious to one of ordinary skill in the art to combine the Yang in view of Li in view of Jing invention with the teachings of Woodruff for the benefit of improve the sound reproduced for a user on a device according to the particular ambient environment, see col. 1 lines 28-34.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Pertinent prior art available on form 892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael Ortiz-Sanchez whose telephone number is (571)270-3711. The examiner can normally be reached Monday- Friday 9AM-6PM.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
/MICHAEL ORTIZ-SANCHEZ/ Primary Examiner, Art Unit 2656
Prosecution Insights