DETAILED ACTION
Continued Examination Under 37 CFR 1.114
1. 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 3/26/2026 has been entered.
Response to Amendment
2. Claims 1, 3, 14, and 20 have been amended, claims 2 and 15 cancelled.
Response to Arguments
3. Applicant’s arguments filed have been fully considered but are moot based on the new grounds of rejection responsive to the amendments.
Claim Rejections - 35 USC § 103
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 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.
6. Claim 1, 3, 5-14, 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Benattar (2016/0162254) in view of Wexler et al (2020/0296521).
Regarding claim 1 Benattar teaches A method (3: audio processing systems; 0060 The system may include an article of manufacture, a method, a system, and an apparatus for an audio customization system) comprising:
capturing a noisy audio signal from an environment of a user, the environment comprising a plurality of people participating in at least one conversation, the plurality of people comprising a person, the noisy audio signal includes audio emitted by a non-human object and audio emitted by the person, wherein the audio emitted by the non-human object comprises a sound-of-interest (81: system may have microphones to detect local audio; 0037: used by friends in a noisy environment such as in a school hallway, a bar/club or at a concert; 54: conversation; 0058: a profile of a police siren may be designated for amplification of audio);
extracting, {by a machine learning model} from the noisy audio signal, based on an acoustic fingerprint (0032: acoustic fingerprinting) a separate audio signal that represents the sound-of-interest, the separate audio signal is isolated from other audio in the noisy audio signal (45: multi-channel digital signal processing to divide ambient sound environment into multiple channels based on frequency ranges, directionality, or audio characteristics, including but not limited to modulation rates that correspond to a wide variety of ambient sounds, including speech; 47;
97: The sample audio may be used to create an audio profile such as a specific voice, machinery, or other noise. Profiles for a noise, such as a jackhammer or a person the user does not want to hear may be created, as well as profiles to a noise or person the user especially want to hear may be created by isolating and analyzing the specified audio to characterize the audio and establish a profile that can be used by the adaptive audio controller 401, to either enhance or attenuate audio corresponding to the characteristics of the sample.);
generating an enhanced audio signal, the enhanced audio signal is based at least on the separate audio signal, wherein said generating comprises ensuring that the separate audio signal is present in the enhanced audio signal (30: It an object to introduce those aspects of the ambient sound environment that a listener identifies as desirable into the source or streamed listening environment, and to make one or more adjustments to enhance the resulting combined sound; 97: enhance audio characteristics of the sample); and
outputting the enhanced audio signal to the user via at least one hearable device (97; [0082] One or more active profiles 103 may be used by the audio customization engine 101 to customize audio signals provided to an audio output device 104, for example, headphones.
[0038] A user may select which sounds are to be heard from both the ambient environment and the source signal);
But does not specifically teach where Wexler teaches
extracting, by a machine learning model from the noisy audio signal, based on an acoustic fingerprint, a separate audio signal (238-239; 240: Then, to separate the speaker's voice from additional speakers or background noise in a noisy audio, a second pre-trained neural network may receive the noisy audio and the speaker's signature, and output an audio (which may also be represented as attributes) of the voice of the speaker as extracted from the noisy audio, separated from the other speech or background noise. It will be appreciated that the same or additional neural networks may be used to separate the voices of multiple speakers.
515: The way these machine-learning algorithms recognize speakers is based on mathematical solutions that use audioprints. The term “audioprint,” also known as “acoustic fingerprint” and “voice signature,” refers to a condensed digital summary of the specific acoustic features of a sound-emanating object (e.g., individuals and also inanimate objects) deterministically generated from a reference audio signal. A common technique for determining an audioprint from recorded audio signals is using a time-frequency graph called a spectrogram. ).
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Wexler and machine learning for audio separation for improved and more efficient separation. Benattar already teaches acoustic fingerprinting (32) and separation (45, 97), and one could look to Wexler to allow for the use of machine learning for fast and efficient speaker separation (Wexler 0238).
Regarding claim 3 Benattar does not specifically teach where Wexler teaches The method of Claim 1, wherein the machine learning model is trained to extract audio signals of human and defined non-human objects (240 separate the speaker's voice from additional speakers or background noise in a noisy audio).
Rejected for similar rationale and reasoning as claim 1
Regarding claim 5 Benattar teaches The method of Claim 1, wherein said capturing is performed by a single microphone or by multiple microphones (0081: one or more microphones).
Regarding claim 6 Benattar teaches The method of Claim 1, wherein the sound-of-interest is at least one of: a ringtone, an alert, a car honk, an alarm, a public announcement, and a siren (0043; 0083: car horns or police sirens).
Regarding claim 7 Benattar teaches The method of Claim 1, wherein the non-human object comprises at least one of: a phone; a public announcement system; a vehicle; and an alarm system (43; 0083: car horns or police sirens).
Regarding claim 8 Benattar teaches The method of Claim 1 further comprises obtaining from the user a list of different types of sounds-of-interests, wherein the user is enabled to selectively turn on and off filtrations of the different types of the sounds-of-interests (Abstract: system allows user to select the profiles; user selection; 26: allow a user to adjust the filtration algorithm or switch among them; 31; 56; 0083: A user control interface 105 operates with a profile manager 106 to designate a set of active profiles.; [0038] A user may select which sounds are to be heard from both the ambient environment and the source signal ).
Regarding claim 9 Benattar teaches The method of Claim 8, wherein said selectively turning on and off the filtrations is performed via a user interface of a mobile device of the user, or based on an automatic computation (abstract; 26; 38; 56; 60; 83).
Regarding claim 10 Benattar teaches The method of Claim 1, wherein said extracting further comprises extracting a second separate audio signal that represents the person (97 person).
Regarding claim 11 Benattar teaches The method of Claim 1, wherein said outputting is performed in a first duration of the at least one conversation, the method further comprising:
during the first duration, obtaining a user indication indicating that the sound-of-interest is no longer of interest to the user (abstract; 26; 38; 56; 60; 83);
subsequently to said obtaining the user indication, capturing a second noisy audio signal from the environment of the user at a second duration of the at least one conversation (37; 54; 81);
outputting a second enhanced audio signal to the user via the at least one hearable device at the second duration, the second duration is after the first duration, the second enhanced audio signal is generated to comprise an audio signal that represents the person, the second enhanced audio signal excludes an audio signal that represents the sound-of-interest, whereby the user is enabled to hear the sound-of-interest in the first duration and to not hear the sound-of-interest in the second duration (82; 97).
Regarding claim 12 Benattar teaches The method of Claim 1, wherein the noisy audio signal comprises a background sound, wherein the enhanced audio signal excludes the background sound or includes a reduced version of the background sound (0031: to filter out unwanted elements of ambient noise not relating to speech; 54: background).
Regarding claim 13 Benattar teaches The method of Claim 12, wherein the background sound is at least one of: a voice of a second person that is different from the person, and a sound of a non-human object that is not an indicated sound-of-interest (0031; 37; 54; 97).
Regarding claim 14 Benattar and Wexler teach A computer program product comprising a non-transitory computer readable storage medium retaining program instructions, which program instructions when read by a processor, cause the processor to:
capture a noisy audio signal from an environment of a user, the environment comprising a plurality of people participating in at least one conversation, the plurality of people comprising a person, the noisy audio signal includes audio emitted by a non-human object and audio emitted by the person, wherein the audio emitted by the non-human object comprises a sound-of-interest;
extract, by a machine learning model, from the noisy audio signal, based on an acoustic fingerprint, a separate audio signal that represents the sound-of-interest, the separate audio signal is isolated from other audio in the noisy audio signal;
generate an enhanced audio signal, the enhanced audio signal is based at least on the separate audio signal, wherein said generating comprises ensuring that the separate audio signal is present in the enhanced audio signal; and
output the enhanced audio signal to the user via at least one hearable device.
Claim recites limitations similar to claim 1 and is rejected for similar rationale and reasoning
Claim 16 recites limitations similar to claim 5 and is rejected for similar rationale and reasoning
Claim 17 recites limitations similar to claim 6 and is rejected for similar rationale and reasoning
Claim 18 recites limitations similar to claim 7 and is rejected for similar rationale and reasoning
Claim 19 recites limitations similar to claim 8 and is rejected for similar rationale and reasoning
Regarding claim 20 Benattar and Wexler teach An apparatus comprising a processor and coupled memory, the processor being adapted to:
capture a noisy audio signal from an environment of a user, the environment comprising a plurality of people participating in at least one conversation, the plurality of people comprising a person, the noisy audio signal includes audio emitted by a non-human object and audio emitted by the person, wherein the audio emitted by the non-human object comprises a sound-of-interest;
extract, by a machine learning model, from the noisy audio signal, based on an acoustic fingerprint, a separate audio signal that represents the sound-of-interest, the separate audio signal is isolated from other audio in the noisy audio signal;
generate an enhanced audio signal, the enhanced audio signal is based at least on the separate audio signal, wherein said generating comprises ensuring that the separate audio signal is present in the enhanced audio signal; and
output the enhanced audio signal to the user via at least one hearable device.
Claim recites limitations similar to claim 1 and is rejected for similar rationale and reasoning
7. Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Benattar in view of Wexler in further view of Barari et al (2019/0005128).
Regarding claim 4 Benattar does not specifically teach The method of Claim 1, wherein said extracting the separate audio signal from the noisy audio signal utilizes a sound retrieval model, the sound retrieval model is trained to retrieve audio based on textual descriptions, wherein the sound retrieval model is provided with a textual description of the audio emitted by the non-human object, causing the sound retrieval model to retrieve the separate audio signal from the noisy audio signal without relying on acoustic fingerprints of the non-human object.
Barari teaches a textual description of audio emitted by the non-human object (retrieve audio based on textual descriptions)
(Barari: 0007: generate one or more audio files matching the one or more scene-objects and the contextual data in real-time by performing a real-time search using textual descriptions;
0020: As an example, consider the scene-theme is “Beach” and the contextual data is “time: 10 PM, rainy season”, then the viewer theme may be “raining night”. Therefore, based on the user inputs or the user preferences that are present under the contextual data, the viewer theme may change.
[0021] Upon determining the viewer theme, the audio generating system, may generate one or more audio files matching the one or more scene-objects and the contextual data in real-time by performing a real-time search using textual descriptions of the one or more scene-objects and the contextual data. From results of the real-time search, the audio generating system may identify one or more relevant audio files from the one or more audio files based on relationship between the scene-theme, the one or more scene-objects, the viewer theme, the contextual data and metadata of the one or more audio files.
0027: Further, the processor 109 may perform real-time search using textual descriptions of the one or more scene-objects and the contextual data to retrieve one or more audio files matching the one or more scene-objects and the contextual data in real-time.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Barari for an improved system for more efficient classification and separation, while presenting a reasonable expectation of success in still allowing for the separation to be performed based on determined sounds.
Benattar already teaches separation (45; 97), storing and identifying sounds (43; 83), and profiles (41).
Barari teaches associating textual descriptions with audio. Thus, one could look to Barari to use the textual descriptions and its associated audio to work in collaboration with / or place into the audio profile of, Benattar, to allow for the classification, retrieval, and separation to take place as described, and teaching
extracting the separate audio signal from the noisy audio signal using a sound retrieval model, the sound retrieval model is trained to retrieve audio based on textual descriptions, wherein the sound retrieval model is provided with a textual description of the audio emitted by the non-human object, causing the sound retrieval model to retrieve the separate audio signal from the noisy audio signal without relying on acoustic fingerprints of the non-human object.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHAUN A ROBERTS whose telephone number is (571)270-7541. The examiner can normally be reached Monday-Friday 9-5 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, Andrew Flanders can be reached on 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.
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 or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHAUN ROBERTS/Primary Examiner, Art Unit 2655
Prosecution Insights