Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
2. In view of Applicant’s argument [Remarks] and amendments filed 07/29/2025, claim rejection(s) with respect to 35 USC 101 have been fully considered and the rejection of claims 1 and 3-21 under 35 U.S.C. 101 is withdrawn.
Response to Arguments
3. Applicant's arguments filed 07/29/2025 have been fully considered but they are not persuasive. Applicant argues that “the Office Action asserts that Every describes processing a captured signal
so that the captured signal and the original signal share at least one parameter (Office Action, p. 11). Specifically, the Office Action asserts that "naturally these two signal would share a large amount of processing parameters due to the fact the [sic] come from the exact same environment" (Id.). However, the Office Action does not point to any portion of Every to support this assertion. Indeed, Every does not disclose or suggest using the parameters of one signal to process another. Every only describes classifying the sub-bands of a signal into either speech or noise and then generating a signal modifier to reduce the noise (Every, col. 5, 11. 5-19). As best understood, Every merely describes determining whether the noise components in a signal and reducing the noise components in that same signal with a generated signal modifier. This differs from performing "audio processing on a captured audio signal using the one or more processing parameters to obtain an adjusted separated source that shares at least one of the one or more processing parameters in common with the residual signal," as recited in amended Claim 1. Accordingly, Every does not disclose or suggest at least this feature. Uhlich and Nagaraja do not cure the deficiencies in Every. Therefore, no combination of these references discloses or suggests every feature recited in amended Claim 1.”
The Examiner respectfully disagrees. Every discloses every aspect of the limitation challenged in the arguments:
“perform audio processing on a captured audio signal…” Every’s audio device captures signals at mics and the system processes them (noise reduction etc.) at Col 3:65-Col 4:23.
“…using the one or more processing parameters…” Every explicitly uses processing parameters typical of an “effect chain” as described in Applicant’s disclosure Col 4:52-59 where the acoustic signals (emphasis added) may be pre-processed in the time-domain and then processed by frequency analysis modules (analogous to pitch estimates in Applicant’s disclosure). The preprocessing also includes pitch estimation, mask (gain) parameters and environment parameters such as echoes and reverb (see Col 9:47-58).
“…to obtain an adjusted separated source…” Every produces a noise-reduced (i.e., adjusted) speech source by subtracting noise/echo and masking the remaining sub-bands (see Col 5:5-19) and then reconstructing (see Col 5:20-27).
“…that shares at least one of the one or more processing parameters in common with the residual signal” Every explicitly discloses the same mask governs both the noise estimate (residual signal) and the masking on the signal path that governs the final noise-subtracted output. When the mask generator generates a multiplicative mask, it is applied by the modifier 312 to the noise subtracted primary acoustic sub-band signals (see Col 8:25-35). Altogether this means the dominance mask/parameterization is shared between the residual noise pathway and the adjusted separated source pathway because both are products of it.
Therefore, the rejection of claims 1 and 3-21 is maintained.
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 (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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
5. Claims 1, 2-3, 15-16 and 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over Every (US 9,378,754) in view of Applicant’s Admitted Prior Art (AAPA) Uhlich et al. "Improving music source separation based on deep neural networks through data augmentation and network blending," and further in view of Nagaraja (US 8,554,551).
Regarding Claim 1:
Every discloses an electronic device comprising circuitry configured to, in real time,
perform source separation on an audio signal (Every: Col 1:41-53 and Col 4:60-Col 5:19 describes a noise reduction system where source separation is performed on an audio signal, isolating a primary signal from background noise);
perform feature extraction on the separated source to obtain one or more processing parameters (Every: Col 6:3-40 derives features (monoaural and binaural) in the analysis path, which is used later as processing parameters. NP-ILD is computed from a noise-cancelled signal and a raw mic signal);
perform audio processing on a captured audio signal using based on the one or more processing parameters to obtain an adjusted separated source that shares at least one of the one or more processing parameters in common with the residual signal (Every: Col 5:20-44, computes a per-sub-band dominance mask and from that computes a noise (residual) estimate, then builds a Wiener/MMSE gain mask that is applied to the noise-subtracted signal and bounded by a residual noise target, because the same dominance decisions, noise estimate and residual target define both the residual and the output, the adjusted separated source (output) shares processing parameters with the residual (noise estimate));
Every does not explicitly disclose a deep neural network, however, AAPA discloses a deep neural network (AAPA: Abstract, Introduction, Fig. 2 and Section 2 discloses with audio source separation using a deep neural network);
It would have been obvious to one of ordinary skill in the art to disclose using a deep neural network for audio source separation by combining Every with AAPA. Every discloses a robust noise suppression system that can be used to reduce unwanted noise signals from a source sound by subtracting the unwanted signal. AAPA discloses using a deep neural network to separate certain signals from another. Both together disclose attempting to separate signals from each other, integrating a deep neural network into Every’s audio processing system as seen in Fig. 3 304 and 310 would be useful because they are commonly used in the art and consistently obtain the best results for tasks such as source audio separation. Therefore, it would have been obvious to Combine Every with AAPA.
Every and AAPA do not explicitly mix residual signal and the adjusted separated source to obtain a mixed audio signal to cause the adjusted separated source to correspond to the separated source; and output the mixed audio signal to another device. However, Nagaraja does disclose these limitations: mix residual signal and the adjusted separated source to obtain a mixed audio signal to cause the adjusted separated source to correspond to the separated source; (Nagaraja: Col 2 lines 40-52 discloses a first signal that is a context-enhanced signal and contains the primary foreground signals, this is combined with a context suppressed signal which has been reduced or removed, leaving background or less prominent elements, it essentially captures what remains after isolating the primary signal (this is interpreted as a residual signal) These signals are then mixed this mixing step reintroduces portions of the background or residual audio with the primary signal, resulting in a combined output that retains the primary audio’s focus while including some ambient or secondary elements for a more balanced sound.)
and output the mixed audio signal to another device (Nagaraja: Col 27 lines 25-45 outputs).
Every and AAPA in view of Nagaraja are combinable because they are both from the same field of endeavor speech processing, e.g., both disclose methods of speech being input to a system and a method for suppressing certain signals and enhancing desired ones. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to disclose mixing an adjusted signal with a residual signal to obtain a mixed audio signal because this is a predictable choice for improving audio clarity and output, that is typical in audio processing system design which is why it is done in Nagaraja.
Regarding Claim 3:
The combination of Every and AAPA further disclose the electronic device of claim 1, wherein the circuitry is configured to perform audio processing on the captured audio signal based on the separated source and the one or more processing parameters to obtain the adjusted separated source (Every: Col 1 lines 41 - 53 and Col 4 line 60 - Col 5 line 19 describes the audio signal is adjusted by classifying the sub-band signals as speech or noise, meaning that the primary signal functions as the separated source. The processing parameters such as the NP-ILD and ILD are used to decide which parts of the signal need to be updated based on what was decided as speech and noise. Pieces of the primary acoustic signal are changed based off of how sub-bands of it are classified and noise reduction may be applied to the areas classified as speech.).
Regarding Claim 15:
The combination of Every and AAPA further disclose the electronic device of claim 1, wherein the captured audio signal is acquired by a microphone or instrument pickup (Every: Fig.1 106 discloses a microphone).
Regarding Claim 16:
The combination of Every and AAPA further disclose the electronic device of claim 15, wherein the microphone is a microphone of a device such as a smartphone, headphones, a TV set, a Blu-ray player (Every: Microphone M1 and M2 are not limited to an particular device, Col 4 lines 24-27 discloses an earpiece headset or handset).
Regarding Claim 20:
Claim 20 has been analyzed with regard to claims 1 above (see rejection above) and
is rejected for the same reasons used above.
Regarding Claim 21:
Every and AAPA disclose a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 20 (Every: Fig. 2 and claim 18).
6. Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Every, in view of AAPA, further in view of Nagaraja and further in view of Short (US 9,443,535).
Regarding Claim 17:
Every, AAPA and Nagaraja further disclose the electronic device of claim 2, wherein the (Every: Col 4 lines 24-27 discloses an earpiece headset or handset which are not limiting and could certainly be a loudspeaker or contain loudspeakers).
Every, AAPA and Nagaraja do not disclose wherein the (Short: Col 72 lines 24-38 describes scenarios where background signals are added back into the processed signal (interpreted as the source signal) This yields an output signal that combines both the target sound and background noise).
Every, APPA and Nagaraja in view of Short are combinable because they are both from the same field of endeavor speech processing, e.g., both disclose methods of speech being input to a system and a method for suppressing certain signals and enhancing desired ones. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to disclose outputting these signals to a loudspeaker. The suggestion/motivation for doing so is “a system that provides for real or near real time signal separation”.
7. Claims 4-7 and 10-14 are rejected under 35 U.S.C. 103 as being unpatentable over Every in view of AAPA, further in view of Nagaraja and further in view of Gao (US 2010/0192753).
Regarding Claim 4:
The combination of Every, AAPA and Nagaraja further disclose the electronic device of claim 1, except wherein the separated source comprises an original vocals signal, the residual signal comprises accompaniment and the captured audio signal comprises a user's vocals signal However, Gao discloses this limitation: (Gao: paragraph [0041-0044] a singing voice and standard song data are considered separate sources of audio data streams, the singing voice being a live newly captured vocal input the MP3 or MIDI data in the standard song is residual signal (accompaniment data) as well as original voice data. It takes the captured audio signal and mixes it with the vocal input to produce a final output).
Every, AAPA, Nagaraja and Gao are combinable because they are both from the same field of endeavor speech processing, e.g., all disclose methods of speech being input to a system and a method for suppressing certain signals and enhancing desired ones. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to disclose outputting these signals to a loudspeaker. The suggestion/motivation for doing so is “provide a karaoke apparatus, which is capable of correcting pitch of the singing voices, adding harmony to produce a harmony effect composed of three voice parts, and providing score and comments for the singing voice so as to produce dulcet timbre and apparent impression for a karaoke singer”.
Regarding Claim 5:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 4, wherein the circuitry is further configured to perform pitch analysis on the original vocals signal to obtain original vocals pitch as processing parameter (Gao: p[0006-0009] the received voice is compared to the pitch of the standard song);
and perform pitch analysis on the user's vocals signal to obtain user's vocals pitch (Gao: p[0006-0009] a pitch correcting system for perform filtering and correcting process for the singing pitch based off of scoring compared to the original track).
Regarding Claim 6:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 5, wherein the circuitry is further configured to a perform vocals pitch comparison based on the user's vocals pitch and on the original vocals pitch to obtain a pitch comparison result (Gao: p[0006-0009] a pitch correcting system for perform filtering and correcting process for the singing pitch based off of scoring compared to the original track).
Regarding Claim 7:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 6, wherein the circuitry is further configured to perform vocals mixing of the original vocals signal with the user's vocals signal based on the pitch comparison result to obtain the adjusted vocals signal (Gao: p[0009] synthetic output is produced by combining pitch correcting system, harmony adding system, and the pitch evaluating system for mixing the voice data output of the three systems).
Regarding Claim 10:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 4, wherein the circuitry is further configured to perform timbrical analysis on the original vocals signal to obtain timbrical information as processing parameter (Gao: [0059] uses timbre as a parameter to modify the data tonally using the timbre correction filter).
Regarding Claim 11:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 10, wherein the circuitry is further configured to perform audio processing on the user's vocals signal based on the timbrical information to obtain the adjusted vocals signal (Gao: p[0081] modification occurs that will affect the timbre of the user’s vocal output).
Regarding Claim 12:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 4, wherein the circuitry is further configured to perform effect chain analysis on the original vocals signal to obtain a chain effect parameter as processing parameter (Every and Gao: wherein Figure 3 blocks 304 306 310 312 and 314 of Every are considered chain analysis as they are chaining effects to enhance parameters and in combination with the reverberation and timbral chains of Gao in Fig. 1 meet this limitation).
Regarding Claim 13:
The combination of Every, AAPA, Nagaraja and Gao further disclose the electronic device of claim 12, wherein the circuitry is further configured to perform audio processing on the user's vocals signal based on the chain effect parameter to obtain the adjusted vocals signal (Every and Gao: Fig. 1 of Gao showing the adjusted signal output to the AV output unit in 14 and Fig. 2 of Every).
Regarding Claim 14:
Every, AAPA and Nagaraja further discloses the electronic device of claim 1, except wherein the circuitry is further configured to compare the captured audio signal with the separated source to obtain a quality score estimation and provide a quality score as feedback to a user based on the quality score estimation. However, Gao discloses this limitation Gao: p[0129-0139] and p[0144-145] discloses evaluation output modules that output a score and comment into the output system 44 and displays them to the user).
Every, AAPA, Nagaraja and Gao are combinable because they are both from the same field of endeavor speech processing, e.g., all disclose methods of speech being input to a system and a method for suppressing certain signals and enhancing desired ones. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to disclose a quality estimation score. The suggestion/motivation for doing so is user satisfaction with the system, which would improve a system focused on user satisfaction by providing immediate feedback, and an overall improved user experience.
8. Claims 8-9 are rejected under 35 U.S.C. 103 as being unpatentable over Every in view AAPA, further in view of Nagaraja, further in view of Gao and further in view of Finauer (11,238,882).
Regarding Claim 8:
Every, AAPA, Nagaraja and Gao further discloses the electronic device of claim 4, except wherein the circuitry is further configured to perform reverberation estimation on the original vocals signal to obtain reverberation time as processing parameter. However, Finauer discloses this limitation: (Finauer: Col 5 lines 1-13 and Col 7 lines 15-59 discloses estimating decay rates during reverberation signal period. Specifically separating the signal into a combined signal period (when tone and reverberation are present) and a reverberation signal period (when ambient signals are present) this allows the system to isolate reverberation components and estimate a decay rate of the ambient signal which correlates to reverberation time and tells it how long it lasts. It then uses this estimated decay rate to adjust the processing of audio signals by applying attenuation and smoothing based on the reverberation period).
Every, AAPA, Nagaraja, Gao and Finauer are combinable because they are both from the same field of endeavor speech processing, e.g., all disclose methods of speech being input to a system and a method for suppressing certain signals and enhancing desired ones. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to disclose using the reverberation time as an input parameter. The suggestion/motivation for doing so is to enhance audio clarity by adapting processing to the acoustic environment. Using reverberation time as an input parameter as show in Finauer allows the system to adjust settings for noise suppression and signal enhancement based on room acoustics. Every and Gao demonstrate methods for suppressing undesired signals and enhancing desired ones, and incorporating reverberation time enables more precise, context-sensitive processing to improve intelligibility and audio quality.
Regarding Claim 9:
Every, AAPA, Nagaraja, Gao and Finauer further disclose the electronic device of claim 8, wherein the circuitry is further configured to perform reverberation on the user's vocals signal based on the reverberation time to obtain the adjusted vocals signal (Finauer: Col 3 18-44 discloses separating an audio input signal into different frequency bins, distinguishing between dry and ambient signal components, and identifying reverberation signal periods. It also explains how the reverberation tail decays exponentially after the tone stop and how reverberation can be estimated by limiting the speed of amplitude changes).
9. Claims 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Every in view AAPA and further in view of Hoffman (US 9,553,683).
Regarding Claim 18:
Every, AAPA and Nagaraja further discloses the electronic device of claim 1, except wherein the separated source comprises a guitar signal, the residual signal comprises a remaining signal and the captured audio signal comprises a user's guitar signal. However, Hoffman discloses this limitation:
(Hoffman: Col 15 lines 10-17 discloses that one of the sources/signals may be from a guitar audio).
Every, AAPA, Nagaraja and Hoffman are combinable because they are both from the same field of endeavor audio processing, e.g., all disclose methods of speech being input to a system and a method for suppressing certain signals and enhancing desired ones. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to disclose using the reverberation time as an input parameter. The suggestion/motivation for doing so is to enhance audio clarity of a diverse array of audio signals not just voices in particular the signals in Hoffman are examples of this and could simply be converted to the methods of Every which discloses processes that can work for multiple types of audio signals, not just vocal.
Regarding Claim 19:
Every, AAPA, Nagaraja and Hoffman further discloses the electronic device of claim 18, wherein the circuitry is further configured to perform distortion estimation on the guitar signal to obtain a distortion parameter, as processing parameter and perform guitar processing on the user's guitar signal based on the guitar signal and the distortion parameter to obtain an adjusted guitar signal (Hoffman: Col 15 discloses signal processing applied to a guitar signal, the concept of analyzing guitar effects or signal modifications to guide playback or output such as delay, distortion or reverb, it also discloses processing input signal using parameters derived from feature extraction (the way to tell if a sound is distorted is to look at the characteristics of its signal)).
Conclusion
THIS ACTION IS MADE FINAL. 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 IAN SCOTT MCLEAN whose telephone number is (703)756-4599. The examiner can normally be reached "Monday - Friday 8:00-5:00 EST, off Every 2nd Friday".
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, Hai Phan can be reached at (571) 272-6338. 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.
/IAN SCOTT MCLEAN/Examiner, Art Unit 2654
/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654
Prosecution Insights