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 request for reconsideration of the finality of the rejection of the last Office action is persuasive and, therefore, the finality of that action is withdrawn.
Rejection under 35 U.S.C. 103
Applicant’s arguments with respect to the rejection(s) of claim(s) 1, 3-10, 12-18, 20, and 24-26 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made.
Claim Rejections - 35 USC § 103
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.
Claims 1, 9-10, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Brown et al. (US 20100179808 A1; hereinafter referred to as Brown1) in view of Faller et al. (US 8275610 B2; hereinafter referred to as Faller), Pradhan et al. (US 20160005401 A1; hereinafter referred to as Pradhan), and Bradley et al. (US 20160099012 A1; hereinafter referred to as Bradley).
Regarding claim 1, Brown1 discloses: performing a second path signal processing, the second path signal processing comprising: performing voice detection on the audio source input and calculating a detection confidence, wherein the detection confidence indicates the possibility of voice in the audio source input ([0004] the method may further include generating a confidence in detecting speech in the center channel and the mixing may include mixing the flattened speech channel with the audio signal proportionate to the confidence of having detected speech);
and calculating a second gain control parameter based on the detection confidence ([0050-0051] The magnitude gain is next modified based on the voice -activity-detector output 21, 22);
and updating the first gain control parameter with the second gain control parameter to provide an updated first gain control parameter, and performing the first path signal processing based on the updated first gain control parameter ([Fig. 1 (21, 22), 0012] while the voice activity detector 13 receives the same input C 20 and produces as output the control signal 22 for variable-gain amplifiers 14a and 14c on the on hand and, on the other, the control signal 21 for variable-gain amplifier 14b) wherein the audio source input comprises a multi-channel source input, and performing voice detection on the audio source input and calculating a detection confidence comprises: extracting a center channel signal from the multi-channel source input… ([0001] Herein are described methods and apparatus for extracting a center channel of sound from an audio signal with multiple channels, for flattening the spectrum of an audio signal, for detecting speech in an audio signal).
Brown1 does not explicitly, but Faller teaches: a method of dynamic voice enhancement, comprising: performing a first path signal processing, the first path signal processing comprising receiving an audio source input and performing dynamic loudness balancing on the audio source input based on a first gain control parameter… ([col 5-6, lines 62-2] Dialogue gain control can also be implemented for home cinema systems with surround sound. One important aspect of dialogue gain control is to detect whether dialogue is in the center channel or not. One way of doing this is to detect if the center has sufficient signal energy such that it is likely that dialogue is in the center channel. If dialogue is in the center channel, then gain can be added to the center channel to control the dialogue volume).
Brown1 and Faller are considered analogous in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1 to combine the teachings of Faller because doing so would allow for improved voice/dialogue enhancement by using different speech features to determine how to adjust and control gain for desired signal components (Faller [col 5, lines 52-58] identification of dialogue component signals based on center-assumption (or generally position-assumption) and spectral range of speech is simple and works well in many cases. The dialogue identification, however, can be modified and potentially improved. One possibility is to explore more features of speech, such as formants, harmonic structure, transients to detect dialogue component signals).
The combination of Brown1 and Faller does not explicitly, but Pradhan teaches: performing normalization on the center channel signal… ([0032] The normalizer 34 is connected to the prosodizer 22. The normalizer 34 receives the speech from the dispatcher 18 via the prosodizer 22. The normalizer receives the speech in the time domain and normalizes the speech according to conventional principles. This normalization can be performed on the center channel signal extracted in Brown1.);
performing a Fourier transformation on a normalized input signal ([0032] The windower 36 receives the speech in the time domain from the normalizer 34 and creates overlapping windows of the speech in the time domain according to a conventional method. The fast Fourier Transform 38 receives the speech from the windower 36 in the time domain and transforms the speech to the frequency domain before entering the speech into the analysis system 26) after performing normalization on the center channel signal to provide a Fourier transformed signal… ([0032] The normalizer 34 is connected to the prosodizer 22. The normalizer 34 receives the speech from the dispatcher 18 via the prosodizer 22. The normalizer receives the speech in the time domain and normalizes the speech according to conventional principles).
Brown1, Faller, and Pradhan are considered analogous in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1 and Faller to combine the teachings of Pradhan because doing so would improve audio processing efficiency by allowing for input audio in the time domain to be adequately scaled using a normalizer, which prevents potential data loss and other errors that can occur from subsequent processes such as windowing and Fourier transforms (Pradhan [0032] The windower 36 receives the speech in the time domain from the normalizer 34 and creates overlapping windows of the speech in the time domain according to a conventional method. The fast Fourier Transform 38 receives the speech from the windower 36 in the time domain and transforms the speech to the frequency domain before entering the speech into the analysis system 26. The fast Fourier Transform 38 is a light transformer in that it is fast Fourier Transform that uses fewer than fifteen, and preferably only twelve features. All further processing of the speech is done in the frequency domain).
The combination of Brown1, Faller, and Pradhan does not explicitly, but Bradley teaches: and performing fast autocorrelation ([0109] The scores may be computed using any of the techniques described above. In some implementations, the scores may be computed using an auto-correlation of the frequency representations, such as an auto-correlation of the magnitude squared of a frequency representation) on the normalized center channel signal ([0100] a portion of a signal is obtained. The signal may be any signal for which it may be useful to estimate features, including but not limited to speech signals or music signals. The portion may be any relevant portion of the signal, and the portion may be, for example, a frame of the signal that is extracted on regular intervals) to provide a result representing the detection confidence ([0109-0110] In some implementations, the scores may be computed using an auto-correlation of the frequency representations, such as an auto-correlation of the magnitude squared of a frequency representation… the fractional chirp rate is estimated by selecting a fractional chirp rate corresponding to a highest score. In some implementations, the estimate of the fractional chirp rate may be refined using iterative techniques, such as golden section search or gradient descent. The estimated fractional chirp rate may then be used for further processing of the signal as described above, such as speech recognition or speaker recognition. The score can represent a detection confidence for speech recognition.), wherein performing the fast autocorrelation on the normalized center channel further comprises… and performing fast autocorrelation on the Fourier transformed signal ([0109] The score may indicate a match between the fractional chirp rate corresponding to the score and the fractional chirp rate of the portion of the signal. The scores may be computed using any of the techniques described above. In some implementations, the scores may be computed using an auto-correlation of the frequency representations, such as an auto-correlation of the magnitude squared of a frequency representation).
Brown1, Faller, Pradhan, and Bradley are considered analogous in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, and Pradhan to combine the teachings of Bradley because doing so would allow for the use of auto-correlation to compute scores representing harmonic amplitude matrix features for frequency representations of an audio signal, leading to more accurate speech/voice recognition using these features (Bradley [0098] For each portion of the signal that is processed, a fractional chirp rate, pitch, and harmonic amplitudes may be determined. Some or all of the fractional chirp rate, pitch, and harmonic amplitudes may be referred to as HAM (harmonic amplitude matrix) features and a feature vector may be created that comprises the HAM features. The feature vector of HAM features may be used in addition to or in place of any other features that are used for processing harmonic signals. For example, the HAM features may be used in addition to or in place of mel-frequency cepstral coefficients, perceptual linear prediction features, or neural network features. The HAM features may be applied to any application of harmonic signals, including but not limited to performing speech recognition, word spotting, speaker recognition, speaker verification, noise reduction, or signal reconstruction).
Regarding claim 9, the combination of Brown1, Faller, Pradhan, and Bradley teaches: the method according to claim 1. Brown1 further teaches: wherein the first path signal processing and the second path signal processing are synchronous or asynchronous ([Fig .1 (17a, 17b), 0012] Respective Discrete Fourier Transformers 18 receives the left and right channels 17a, 17b of the input signal 17 as input and produces as output the transforms 19a, 19b. The center - channel extractor 11 receives the transforms 19 and produces as output the phantom center channel C 20. The spectral flattener 12 receives as input the phantom center channel C 20 and produces as output the shaped center channel! 24, while the voice activity detector 13 receives the same input C 20 and produces as output the control signal 22 for variable-gain amplifiers 14a and 14c on the on hand and, on the other, the control signal 21 for variable -gain amplifier 14b).
Regarding claim 10, Brown1 discloses: a system of dynamic voice enhancement, comprising: a memory configured to store computer-executable instructions; and a processor configured to execute the computer-executable instructions to perform ([0066] The computer 4 includes a memory 41, a CPU 42 and a bus 43. The bus 43 communicatively couples the memory 41 and CPU 42. The memory 41 stores a computer program for executing any of the methods described above). The rest of the claim recites similar limitations as claim 1 and therefore is rejected similarly.
Regarding claim 18, it recites similar limitations as claims 1 and 10 and therefore is rejected similarly.
Claims 3, 12, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Brown1 in view of Faller, Pradhan, and Bradley as applied to claims 1, 9-10, and 18 above, and further in view of Wu et al. (US 11164592 B1; hereinafter referred to as Wu).
Regarding claim 3, the combination of Brown1, Faller, Pradhan, and Bradley teaches: the method according to claim 1. The combination of Brown1, Faller, Pradhan, and Bradley does not explicitly, but Wu teaches: wherein the calculating a second gain control parameter based on the detection confidence comprises: calculating the second gain control parameter based on a logarithmic function of the detection confidence ([col 9 ,lines 57-63] the device 110 may determine the loudness values (e.g., RMS values) using a logarithmic scale instead of a linear scale. Thus, the loudness values (e.g., instant loudness value, loudness estimate, noise estimate, etc.) may be measured in decibels (dB), as this improves an accuracy of the loudness measurement 430 and makes it easier to tune parameters of the loudness measurement);
smoothing the calculated second gain control parameter to provide a smoothed second gain control parameter ([col 13, lines 48-49] The gain estimator 440 may apply smoothing to the instantaneous gain value to generate a smoothed gain value);
and limiting the smoothed second gain control parameter ([col 20, lines 57-64] device 110 may determine (1218) a loudness estimate value, may determine (1220) a target loudness value, may determine (1222) an adaptive gain corresponding to the loudness estimate value and the target loudness value, may optionally (1224) smooth the adaptive gain over time, and may optionally (1226) clamp and limit the adaptive gain to avoid excessively loud output or distortion).
Brown1, Faller, Pradhan, Bradley, and Wu are considered analogous in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, Pradhan, and Bradley to combine the teachings of Wu because doing so would improve user experience and overall sound quality by using a smoothed gain control to balance audio volume (Wu [col 2, lines 43-46] To improve a user experience and sound quality of audio data, devices, systems and methods are disclosed that perform automatic gain control (AGC) using different decay rates).
Regarding claim 12, it recites similar limitations as claim 3 and therefore is rejected similarly.
Regarding claim 20, it recites similar limitations as claim 3 and therefore is rejected similarly.
Claims 4-5 and 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Brown1, Faller, Pradhan, and Bradley, as applied to claims 1, 9-10, and 18 above, and further in view of Brown (US 9324337 B2; hereinafter referred to as Brown2).
Regarding claim 4, the combination of Brown1, Faller, Pradhan, and Bradley teaches: the method according to claim 1. Brown1 further teaches: wherein the audio source input comprises a multi-channel source input, and the performing dynamic loudness balancing on the audio source input comprises: extracting a center channel signal from the multi-channel source input ([0001] Herein are described methods and apparatus for extracting a center channel of sound from an audio signal with multiple channels);
and concatenating and mixing the enhanced center channel signal and the reduced other channel signals to generate an output signal ([0004] A method for enhancing speech may include extracting a center channel of an audio signal, flattening the spectrum of the center channel and mixing the flattened speech channel with the audio signal, thereby enhancing any speech in the audio signal).
The combination of Brown1, Faller, Pradhan, and Bradley does not explicitly, but Brown2 teaches: enhancing a loudness of the center channel signal to provide an enhanced center channel signal and reducing a loudness of other channel signals to provide reduced other channels based on the first gain control parameter or the updated first gain control parameter ([col 1, lines 18-26] the invention is a method and system for improving clarity and/or intelligibility of dialog determined by a stereo input signal by analyzing the input signal to generate filter control values, upmixing the input signal to generate a speech (center) channel and non-speech channels, filtering the speech channel in a peaking filter (steered by at least one of the control values) and attenuating the non-speech channels in a manner also steered by at least some of the control values).
Brown1, Faller, Pradhan, Bradley, and Brown2 are considered analogous art in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, Pradhan, and Bradley to combine the teachings of Brown2 because doing so would efficiently improve the clarity of dialogue in the audio signal by using an analysis module and filtering subsystem to enhance a center channel (Brown2 [col 3, lines 7-11] Typical embodiments of the present invention achieve improved dialog intelligibility with reduced computational requirements relative to conventional methods and systems designed to improve dialog intelligibility).
Regarding claim 5, the combination of Brown1, Faller, Pradhan, Bradley, and Brown2 teaches: the method according to claim 4. Brown1 further teaches: further comprising: performing crossover filtering on the audio source input before performing the dynamic loudness balancing ([0024] Auditory filters separate the speech in the presumed speech channel into perceptual bands).
Regarding claim 13, it recites similar limitations as claim 4 and therefore is rejected similarly.
Regarding claim 14, it recites similar limitations as claim 5 and therefore is rejected similarly.
Claims 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Brown1, Faller, Pradhan, Bradley, and Brown2 as applied to claims 4-5 and 13-14 above, and further in view of Chen et al. (WO 2012064764 A1; hereinafter referred to as Chen).
Regarding claim 6, the combination of over Brown1, Faller, Pradhan, Bradley, and Brown2 teaches: the method according to claim 5. Brown1 further teaches: and concatenating and mixing signals in a low frequency range and ahigh frequency range of the audio source input and signals in the mid frequency range of the audio source input after the dynamic loudness balancing to generate an output signal ([0004] A method for enhancing speech may include extracting a center channel of an audio signal, flattening the spectrum of the center channel and mixing the flattened speech channel with the audio signal, thereby enhancing any speech in the audio Signal).
The combination of over Brown1, Faller, Pradhan, Bradley, and Brown2 does not explicitly, but Chen discloses: performing the dynamic loudness balancing only on signals in a mid frequency range of the audio source input ([0047] In one embodiment, the coefficients increase gain over a middle frequency band relative to lower and upper frequency bands).
Brown1, Faller, Pradhan, Bradley, Brown2, and Chen are considered analogous art in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, Pradhan, Bradley, Brown2 to combine the teachings of Chen because doing so would maintain speech intelligibility despite other ambient noise in the audio signal using output gain, leading to enhanced speech audio (Chen [0005] The downlink audio signal is also modified by adjusting its overall loudness in accordance with the determined overall output gain. This may enable the speech that is in the downlink voice signal to remain intelligible despite widely varying ambient noise levels during the call and without requiring the user to make many adjustments to the volume setting).
Regarding claim 15, it recites similar limitations as claim 6 and therefore is rejected similarly.
Claims 7 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Brown1, Faller, Pradhan, and Bradley, as applied to claims 1, 9-10, and 18 above, and further in view of Visser (US 20110058676 A1; hereinafter referred to as Visser).
Regarding claim 7, the combination of Brown1, Faller, Pradhan, and Bradley teaches: the method according to claim 1. The combination of Brown1, Faller, Pradhan, and Bradley does not explicitly, but Visser discloses: wherein the audio source input further comprises a dual- channel source input ([0007] The first signal includes at least two channels of the multichannel signal), and the method further comprises generating a multi- channel source input based on the dual- channel source input ([0007] An apparatus, according to a general configuration, for processing a multichannel signal that includes a directional component has a first filter configured to perform a first directionally selective processing operation on a first signal to produce a residual Signal).
Brown1, Faller, Pradhan, Bradley, and Visser are considered analogous art in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, Pradhan, and Bradley to combine the teachings of Visser because doing so would address reverberation in a multichannel audio signal, leading to clearer and more accurate speech/voice detection (Visser [0005] Reverberated speech generally sounds more muffled, less clear, and/or less intelligible than speech heard in a face -to-face conversation (e.g., due to destructive interference of the signal instances on the various acoustic paths). These effects may be particularly problematic for automatic speech recognition (ASR) applications (e.g., automated business transactions, such as account balance or stock quote checks; automated menu navigation; automated query processing), leading to a reduction in accuracy. Therefore it may be desirable to perform a dereverberation operation on a recorded signal while minimizing changes to the voice color).
Regarding claim 16, it recites similar limitations as claim 7 and therefore is rejected similarly.
Claims 8 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Brown1, Faller, Pradhan, Bradley, and Visser, as applied to claims 7 and 16 above, and further in view of Tashev et al. (US 20090316929 A1; hereinafter referred to as Tashev).
Regarding claim 8, the combination of Brown1, Faller, Pradhan, Bradley, and Visser teaches: the method according to claim 7. The combination of Brown1, Faller, Pradhan, Bradley, and Visser does not explicitly, but Tashev discloses: wherein the generating a multi-channel source input based on the dual-channel source input comprises: performing across-correlation between a left channel signal and a right channel signal ([0052] In one example, the delay is estimated as the maximum of a Phase Transform (PHAT) weighted and band limited cross correlation function of the two input channels (e.g., front and rear). The resultant delay estimate between front and rear frequency domain audio signals can be used to distinguish signals) from the dual-channel source input;
and generating the multi-channel source input ([0025] The audio processing architecture of FIG. 3 comprises a front channel (e.g., comprising: 302, 308, 314, 318) and a rear channel (e.g., comprising: 304, 310, 316, 320) for respective front and rear channel processing) according to a combination ratio, wherein the combination ratio ([0045] if the ratio of the RMS signal level to the noise floor level is greater than 3.0 (514), than the voice activity flag Vis set equal to a value of 1, indicating that the captured signal is speech (e. g., voice) 516) depends on the cross-correlation.
Brown1, Faller, Pradhan, Bradley, Visser, and Tashev are considered analogous art in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, Pradhan, Bradley, and Visser to combine the teachings of Tashev because doing so would reduce ambient noise and improve sound quality by using an algorithm to reduce noise of captured audio signals (Tashev [0003] The perceptual quality of desired audio signals (E.g., human voice) captured by an electronic device is improved by reducing ambient noise according to an algorithm that acts upon audio signals captured from a front and rear direction. More particularly, audio signals captured by two directional microphones pointing in opposite directions (e.g., a front microphone configured to receive audio signals from a forward direction and a rear microphone configured to receive audio signals from a rear direction) are classified and subsequently enhanced according to the probability of their source (e.g., front or rear), thereby providing an improved quality sound recording than each microphone individually).
Regarding claim 17, it recites similar limitations as claim 8 and therefore is rejected similarly.
Claims 24-26 are rejected under 35 U.S.C. 103 as being unpatentable over Brown1, Faller, Pradhan, and Bradley, as applied to claims 1, 9-10, and 18 above, and further in view of Vasilache et al. (US 20110016077 A1; hereinafter referred to as Vasilache).
Regarding claim 24, the combination of Brown1, Faller, Pradhan, and Bradley teaches: the method of claim 1. The combination of Brown1, Faller, Pradhan, and Bradley does not explicitly, but Vasilache teaches: wherein the normalized center channel is based on at least one of a mean ([0139] the mean value which is used to normalise the absolute sample values of the audio signal may be obtained by determining a long term tracking mean value which is updated periodically. The long term tracking mean value may then be used to normalise samples of the audio signal) and variance ([0144] the variance value used to normalise the audio signal may also be obtained by maintaining a long term tracking variance value which is updated periodically. The long term tracking variance value may then be used to normalise samples of the audio signal.) of input signals corresponding to one of a plurality of time frames ([0143] The process of calculating the mean for a current frame of k samples and then updating the long term tracking mean are shown as processing steps 503 and 505 in FIG. 5.).
Brown1, Faller, Pradhan, Bradley, and Vasilache are considered analogous art in the field of audio processing. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Brown1, Faller, Pradhan, and Bradley to combine the teachings of Vasilache because doing so would allow for better classification of an audio signal using normalization to enhance speech audio (Vasilache [0208] if the audio signal exhibits music like characteristics as determined by the audio signal classifier 260 then it may be preferable to select the super wideband extension layer (L6m) for transmission by the bit stream formatter 256. Alternatively if the audio signal classifier 260 determines the audio signal to be speech like then the bit stream formatter may select the stereo enhancement layer (L6s) for transmission).
Regarding claim 25, it recites similar limitations as claim 24 and therefore is rejected similarly.
Regarding claim 26, it recites similar limitations as claim 24 and therefore is rejected similarly.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nathan Tengbumroong whose telephone number is (703)756-1725. The examiner can normally be reached Monday - Friday, 11:30 am - 8:00 pm 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, 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.
/NATHAN TENGBUMROONG/Examiner, Art Unit 2654
/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654
Prosecution Insights