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) 1-20 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.
Applicant cancelled claim 20 and therefor the 101 rejection has been withdrawn.
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.
Claim(s) 1-3, 9-10 and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Markovic U.S. PAP2018/0301160 A1 in view of in Lim KR 20110126277 A1.
Regarding claim 1 Markovic teaches a speech signal processing method (signal processing apparatus and method are provided for separating a plurality of mixture signals, see abstract), comprising: acquiring a speech observation signal collected by a speech collection device (plurality of mixture signals, see par. [0058]); and performing blind source separation on the speech observation signal according to the first pre-separation signal to obtain a first source speech signal of the sound source of the first pre-separation signal (a first blind source separator 205A based on a first blind source separation technique or algorithm, see par. [0059]); and performing blind source separation on the speech observation signal according to the second pre-separation signal to obtain a second source speech signal of the sound source of the second pre-separation signal ( a second blind source 205N separator based on a second blind source separation technique or algorithm different to the first blind source separation technique, see par. [0059]).
However Markovich does not teach pre-separating the speech observation signal based on distance to obtain a first pre-separation signal and a second pre-separation signal, wherein a first distance between a sound source of the first pre-separation signal and the speech collection device is different from a second distance between a sound source of the second pre-separation signal and the speech collection device.
IN the same field of endeavor Lim teaches an apparatus and a method for improving the sound quality of a portable terminal of the present invention. In particular, by using two microphones, signals generated from different distances are separated to remove noise, and thus, together with a voice signal of a user in a conventional portable terminal. An apparatus and method for removing ambient noise generated., see par. [0001].
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention with the teachings of Lim for the benefit of improving the sound quality of a portable terminal, see par. [0001].
Regarding claim 2 Markovic teaches the speech signal processing method according to claim 1, wherein the speech collection device comprises a plurality of speech collection units (multiple microphones, see par. [0003]); the speech observation signal comprises a first speech observation signal collected by a first speech collection unit (microphone, see par. [0003]); the first speech collection unit being a member of the plurality of speech collection units (The mixing system 10 can be described by a mixing matrix H, which represents all acoustic propagation paths from the original acoustic sources in the room, i.e. the source signals 11 s.sub.1, . . . s.sub.p, to the P sensors, e.g. microphones, see par. [0007]), wherein pre-separating the speech observation signal to obtain the first pre-separation signal and the second pre-separation signal comprises: pre-separating the first speech observation signal to obtain a first pre-separation signal and a second pre-separation signal (ick up the mixture signals 101 x.sub.1, . . . , x.sub.p. The demixing system 100 can be described by a demixing matrix W representing the digital signal processing system which generates the output signals 103 y.sub.1, . . . y.sub.p, see par. [0007]).
Regarding claim 3 Markovic teaches the speech signal processing method according to claim 2, further comprising: randomly selecting one speech collection unit from the plurality of speech collection units as the first speech collection unit (P sensors e.g. microphones, see par. [0007]; any output signals as well as any additional blind source separators, see par. [0065])).
Regarding claim 9 Markovic teaches an electronic apparatus (signal processing apparatus and method are provided for separating a plurality of mixture signals, see abstract), comprising: at least one processor (see claim 1); and a memory in communication with the at least one processor, wherein the memory stores instructions executable by the at least one processor ( a memory storing instructions that when executed by the processor configure the processor to function as a plurality of blind source separators, a combiner, and an adjuster, see claim 1), and the instructions are executed by the at least one processor to allow the at least one processor to: acquire a speech observation signal collected by a speech collection device (plurality of mixture signals, see par. [0058]); and perform blind source separation on the speech observation signal according to the first pre-separation signal to obtain a first source speech signal of the sound source of the first pre-separation signal (a first blind source separator 205A based on a first blind source separation technique or algorithm, see par. [0059]); and perform blind source separation on the speech observation signal according to the second pre-separation signal to obtain a second source speech signal of the sound source of the second pre-separation signal ( a second blind source 205N separator based on a second blind source separation technique or algorithm different to the first blind source separation technique, see par. [0059]).
However Markovich does not teach pre-separating the speech observation signal based on distance to obtain a first pre-separation signal and a second pre-separation signal, wherein a first distance between a sound source of the first pre-separation signal and the speech collection device is different from a second distance between a sound source of the second pre-separation signal and the speech collection device.
IN the same field of endeavor Lim teaches an apparatus and a method for improving the sound quality of a portable terminal of the present invention. In particular, by using two microphones, signals generated from different distances are separated to remove noise, and thus, together with a voice signal of a user in a conventional portable terminal. An apparatus and method for removing ambient noise generated., see par. [0001].
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention with the teachings of Lim for the benefit of improving the sound quality of a portable terminal, see par. [0001].
Regarding claim 10 Markovic teaches the electronic apparatus according to claim 9, wherein the speech collection device comprises a plurality of speech collection units (multiple microphones, see par. [0003]); the speech observation signal comprises a first speech observation signal collected by a first speech collection unit (microphone, see par. [0003]); the first speech collection unit being a member of the plurality of speech collection units (The mixing system 10 can be described by a mixing matrix H, which represents all acoustic propagation paths from the original acoustic sources in the room, i.e. the source signals 11 s.sub.1, . . . s.sub.p, to the P sensors, e.g. microphones, see par. [0007]), wherein pre-separating the speech observation signal to obtain the first pre-separation signal and the second pre-separation signal comprises: pre-separating the first speech observation signal to obtain a first pre-separation signal and a second pre-separation signal (ick up the mixture signals 101 x.sub.1, . . . , x.sub.p. The demixing system 100 can be described by a demixing matrix W representing the digital signal processing system which generates the output signals 103 y.sub.1, . . . y.sub.p, see par. [0007]).
Regarding claim 19 Markovic teaches a non-transitory computer-readable storage medium having stored therein computer instructions that cause a computer to implement the speech signal processing method according to claim 1 (non-transitory computer readable medium, see claim 15).
Claim(s) 4-8, 11-15, 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Markovic U.S. PAP2018/0301160 A1 in view of Lim KR 20110126277 A1, , further in view of Wingate U.S. PAP 2017/0178664 A1.
Regarding claim 4 Markovic teaches the speech signal processing method according to claim 2, wherein pre-separating the first speech observation signal to obtain the first pre-separation signal and the second pre-separation signal comprises: inputting the first speech observation signal into a pre-separation model to obtain the first pre-separation signal and the second pre-separation signal output by the pre-separation model (estimate the MIMO mixing system using only the available microphone signals, which is also known as blind MIMO system identification, see par. [0005]); wherein: the pre-separation model is obtained through deep learning training by using a training set, and the training set comes from the plurality of speech collection units (It has been shown that there is a fundamental relation between a blind MIMO system identification and a broadband blind source separation (BSS) for convolutive mixtures , see par. [0006]); However Markovic does not teach the training set comprises a plurality of samples, and one speech collection unit corresponds to at least one sample, each sample of the at least one sample comprising: a sample observation signal collected by the speech collection unit, and a first sample speech signal and a second sample speech signal both corresponding to the sample observation signal; and a third distance between a sound source of the first sample speech signal and the speech collection unit is different from a fourth distance between a sound source of the second sample speech signal and the speech collection unit.
In the same field of endeavor Wingate teaches an efficient and fast manner for performing source separation on large sets of quickly changing data, see abstract.
Wingate teaches the training set comprises a plurality of samples, and one speech collection unit corresponds to at least one sample, each sample of the at least one sample (the first model may be any classifier configured (e.g. designed and/or trained) to predict value(s) of the property. For example, the first model could comprise a neural network model, such as e.g. a deep neural net (DNN) model, see par. [0025]) comprising: a sample observation signal collected by the speech collection unit, and a first sample speech signal and a second sample speech signal both corresponding to the sample observation signal (operation of the signal separation phase finds the components of the model to best match the distribution determined from the observed signals, see par. [0107]); and a third distance between a sound source of the first sample speech signal and the speech collection unit is different from a fourth distance between a sound source of the second sample speech signal and the speech collection unit (an optimization to minimize a distance between the distribution p( ) determined from the actually observed signals, and q( ) formed from the structured components, the distance function being represented as D(p(f,n,d)∥q(f,n,d)). A number of different distance functions may be used, see par. [0107]).
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention ith the teachings of Wingate for the benefit of efficiently and fast manner for performing source separation on large sets of quickly changing data, see abstract.
Regarding claim 5 Markovic teaches the speech signal processing method according to claim 1, wherein performing the blind source separation on the speech observation signal according to the first pre-separation signal to obtain the first source speech signal of the sound source of the first pre-separation signal comprises: determining a variance term of a probability density function of a sound source corresponding to the speech observation signal (second blind source separator is based on an efficient multivariate time-frequency algorithm, see par. [0074]).
However Markovic does not teach taking the first pre-separation signal as a pilot signal of the variance term of the probability density function of the sound source to obtain the variance term of the probability density function of the sound source into which the pilot signal is introduced; performing blind source separation on the speech observation signal according to a first separation matrix to obtain an initial separation signal frequency vector; determining a first separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix; and determining the first source speech signal according to the first separation signal frequency vector.
Wingate teaches taking the first pre-separation signal as a pilot signal of the variance term of the probability density function of the sound source to obtain the variance term of the probability density function of the sound source into which the pilot signal is introduced ( a directional histogram P(d|n) is formed representing the directions from which the different frequency components at time frame n originated from, see par. [0133]; Another approach is to consider the collection of all directional histograms over time and analyze which directions tend to increase or decrease in weight together. One way to do this is to compute the sample covariance or correlation matrix of these histograms, see par. [0136]); performing blind source separation on the speech observation signal according to a first separation matrix to obtain an initial separation signal frequency vector (NN NTF is based on recognition that the NTF method for acoustic source separation described above can be viewed as a composite model in which each acoustic source is modeled via an NMF decomposition and these sources are combined according to an outer model that takes into account direction, itself a form of NMF, see par. [0142]); determining a first separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix ( Directional NMF because it can be viewed as a plain NMF decomposition of an D×FN matrix into a D×S matrix times an S×FN matrix. This is a decomposition which does not enforce any structure on the magnitude spectrograms of the sources, see par. [0158]); and determining the first source speech signal according to the first separation signal frequency vector (each time frame of the output could be predicted based on the corresponding time frame of the input, or based on a window of the input, see par. [0160]).
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention ith the teachings of Wingate for the benefit of efficiently and fast manner for performing source separation on large sets of quickly changing data, see abstract.
Regarding claim 6 Wingate teaches the speech signal processing method according to claim 5, wherein determining the first separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix, comprises: taking the initial separation signal frequency vector as the first separation signal frequency vector, in case that the initial separation signal frequency vector satisfies a preset condition (the source separation method 400 may begin with an initialization stage 410. Stage 410 may include several initialization steps, at least some of which may occur in any order, see par. [0170]); updating a reference term according to the first separation matrix and acquiring an updated reference term, in case that the initial separation signal frequency vector does not satisfy the preset condition (the quantities M.sub.s(f,n) may be viewed as soft masks because their value in each time-frequency bin is a number between zero and one, inclusive. In other implementations, one may modify the mask, such as by applying a threshold to it to produce a hard mask, which only takes values zero and one, see par. [0186]), wherein the reference term comprises the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix is related to the initial reference term (In step 428 of the iteration stage 420, which, again, may be performed substantially the same for both, basic NTF and NN NTF, approaches, other model parameters may be updated., see par. [0183]); and determining a second separation matrix according to the updated reference term (to that end, e.g. q(s) may be updated to reflect relative total energy in the different acoustic sources and q(d|s) may be updated to be the weighted histogram given by weighting the directions D(f,n) according to weights Xs′(f,n), see par. [0183]); performing blind source separation on the speech observation signal according to the second separation matrix until a separation signal frequency vector obtained by the blind source separation satisfies the preset condition (Steps 422-428 of the iteration stage 420 are iterated for a number of times, e.g. for a certain number of iterations (either predefined or dynamically defined), until one or more predefined convergence conditions is(are) satisfied, see par. [0184]); and taking the separation signal frequency vector obtained as the first separation signal frequency vector (Once the iterations are finished, the method may then proceed to stage 430 where values of the model parameters q(s), q(d|s), and q(f,n|s) available after the iteration stage 420 are used to generate, for each source of interest, a respective mask for identifying contributions from the source to the characteristics X, see par. [0185]).
Regarding claim 7 Wingate teaches the speech signal processing method according to claim 1, wherein performing the blind source separation on the speech observation signal according to the second pre-separation signal to obtain the second source speech signal of the sound source of the second pre-separation signal, comprises: determining a variance term of a probability density function of a sound source corresponding to the speech observation signal ( a directional histogram P(d|n) is formed representing the directions from which the different frequency components at time frame n originated from, see par. [0133]; Another approach is to consider the collection of all directional histograms over time and analyze which directions tend to increase or decrease in weight together. One way to do this is to compute the sample covariance or correlation matrix of these histograms, see par. [0136]); taking the second pre-separation signal as a pilot signal of the variance term of the probability density function of the sound source to obtain the variance term of the probability density function of the sound source into which the pilot signal is introduced; performing blind source separation on the speech observation signal according to a first separation matrix to obtain an initial separation signal frequency vector (NN NTF is based on recognition that the NTF method for acoustic source separation described above can be viewed as a composite model in which each acoustic source is modeled via an NMF decomposition and these sources are combined according to an outer model that takes into account direction, itself a form of NMF, see par. [0142]); determining a second separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix (to that end, e.g. q(s) may be updated to reflect relative total energy in the different acoustic sources and q(d|s) may be updated to be the weighted histogram given by weighting the directions D(f,n) according to weights Xs′(f,n), see par. [0183]); and determining the second source speech signal according to the second separation signal frequency vector (the source separation method 400 may begin with an initialization stage 410. Stage 410 may include several initialization steps, at least some of which may occur in any order, see par. [0170]).
Regarding claim 8 Wingate teaches the speech signal processing method according to claim 7, wherein determining the second separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix, comprises: taking the initial separation signal frequency vector as the second separation signal frequency vector, in case that the initial separation signal frequency vector satisfies a preset condition (the source separation method 400 may begin with an initialization stage 410. Stage 410 may include several initialization steps, at least some of which may occur in any order, see par. [0170]); updating a reference term according to the first separation matrix and acquiring an updated reference term, in case that the initial separation signal frequency vector does not satisfy the preset condition, wherein the reference term comprises the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix is related to the initial reference term (the quantities M.sub.s(f,n) may be viewed as soft masks because their value in each time-frequency bin is a number between zero and one, inclusive. In other implementations, one may modify the mask, such as by applying a threshold to it to produce a hard mask, which only takes values zero and one, see par. [0186]; In step 428 of the iteration stage 420, which, again, may be performed substantially the same for both, basic NTF and NN NTF, approaches, other model parameters may be updated., see par. [0183]); and determining a second separation matrix according to the updated reference term (to that end, e.g. q(s) may be updated to reflect relative total energy in the different acoustic sources and q(d|s) may be updated to be the weighted histogram given by weighting the directions D(f,n) according to weights Xs′(f,n), see par. [0183]); performing blind source separation on the speech observation signal according to the second separation matrix until a separation signal frequency vector obtained by the blind source separation satisfies the preset condition (Steps 422-428 of the iteration stage 420 are iterated for a number of times, e.g. for a certain number of iterations (either predefined or dynamically defined), until one or more predefined convergence conditions is(are) satisfied, see par. [0184]); and taking the separation signal frequency vector obtained as the second separation signal frequency vector (Once the iterations are finished, the method may then proceed to stage 430 where values of the model parameters q(s), q(d|s), and q(f,n|s) available after the iteration stage 420 are used to generate, for each source of interest, a respective mask for identifying contributions from the source to the characteristics X, see par. [0185]).
Regarding claim 11 Markovic teaches the electronic apparatus according to claim 10, wherein the at least one processor is configured to input the first speech observation signal into a pre-separation model to obtain the first pre-separation signal and the second pre-separation signal output by the pre-separation model, wherein:
the pre-separation model is obtained through deep learning training by using a training set, and the training set comes from the plurality of speech collection units (It has been shown that there is a fundamental relation between a blind MIMO system identification and a broadband blind source separation (BSS) for convolutive mixtures , see par. [0006]); However Markovic does not teach the training set comprises a plurality of samples, and one speech collection unit corresponds to at least one sample, each sample of the at least one sample comprising: a sample observation signal collected by the speech collection unit, and a first sample speech signal and a second sample speech signal both corresponding to the sample observation signal; and a third distance between a sound source of the first sample speech signal and the speech collection unit is different from a fourth distance between a sound source of the second sample speech signal and the speech collection unit.
In the same field of endeavor Wingate teaches an efficient and fast manner for performing source separation on large sets of quickly changing data, see abstract.
Wingate teaches the training set comprises a plurality of samples, and one speech collection unit corresponds to at least one sample, each sample of the at least one sample (the first model may be any classifier configured (e.g. designed and/or trained) to predict value(s) of the property. For example, the first model could comprise a neural network model, such as e.g. a deep neural net (DNN) model, see par. [0025]) comprising: a sample observation signal collected by the speech collection unit, and a first sample speech signal and a second sample speech signal both corresponding to the sample observation signal (operation of the signal separation phase finds the components of the model to best match the distribution determined from the observed signals, see par. [0107]); and a third distance between a sound source of the first sample speech signal and the speech collection unit is different from a fourth distance between a sound source of the second sample speech signal and the speech collection unit (an optimization to minimize a distance between the distribution p( ) determined from the actually observed signals, and q( ) formed from the structured components, the distance function being represented as D(p(f,n,d)∥q(f,n,d)). A number of different distance functions may be used, see par. [0107]).
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention ith the teachings of Wingate for the benefit of efficiently and fast manner for performing source separation on large sets of quickly changing data, see abstract.
Regarding claim 12 Markovic teaches the electronic apparatus according to claim 9, wherein the at least one processor is configured to: determine a variance term of a probability density function of a sound source corresponding to the speech observation signal (second blind source separator is based on an efficient multivariate time-frequency algorithm, see par. [0074]).
However Markovic does not teach taking the first pre-separation signal as a pilot signal of the variance term of the probability density function of the sound source to obtain the variance term of the probability density function of the sound source into which the pilot signal is introduced; performing blind source separation on the speech observation signal according to a first separation matrix to obtain an initial separation signal frequency vector; determining a first separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix; and determining the first source speech signal according to the first separation signal frequency vector.
Wingate teaches taking the first pre-separation signal as a pilot signal of the variance term of the probability density function of the sound source to obtain the variance term of the probability density function of the sound source into which the pilot signal is introduced ( a directional histogram P(d|n) is formed representing the directions from which the different frequency components at time frame n originated from, see par. [0133]; Another approach is to consider the collection of all directional histograms over time and analyze which directions tend to increase or decrease in weight together. One way to do this is to compute the sample covariance or correlation matrix of these histograms, see par. [0136]); performing blind source separation on the speech observation signal according to a first separation matrix to obtain an initial separation signal frequency vector (NN NTF is based on recognition that the NTF method for acoustic source separation described above can be viewed as a composite model in which each acoustic source is modeled via an NMF decomposition and these sources are combined according to an outer model that takes into account direction, itself a form of NMF, see par. [0142]); determining a first separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix ( Directional NMF because it can be viewed as a plain NMF decomposition of an D×FN matrix into a D×S matrix times an S×FN matrix. This is a decomposition which does not enforce any structure on the magnitude spectrograms of the sources, see par. [0158]); and determining the first source speech signal according to the first separation signal frequency vector (each time frame of the output could be predicted based on the corresponding time frame of the input, or based on a window of the input, see par. [0160]).
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention ith the teachings of Wingate for the benefit of efficiently and fast manner for performing source separation on large sets of quickly changing data, see abstract.
Regarding claim 13 Wingate teaches the electronic apparatus according to claim 12, wherein the at least one processor is configured to: take the initial separation signal frequency vector as the first separation signal frequency vector, in case that the initial separation signal frequency vector satisfies a preset condition (the source separation method 400 may begin with an initialization stage 410. Stage 410 may include several initialization steps, at least some of which may occur in any order, see par. [0170]); update a reference term according to the first separation matrix and acquiring an updated reference term, in case that the initial separation signal frequency vector does not satisfy the preset condition (the quantities M.sub.s(f,n) may be viewed as soft masks because their value in each time-frequency bin is a number between zero and one, inclusive. In other implementations, one may modify the mask, such as by applying a threshold to it to produce a hard mask, which only takes values zero and one, see par. [0186]), wherein the reference term comprises the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix is related to the initial reference term (In step 428 of the iteration stage 420, which, again, may be performed substantially the same for both, basic NTF and NN NTF, approaches, other model parameters may be updated., see par. [0183]); and determine a second separation matrix according to the updated reference term (to that end, e.g. q(s) may be updated to reflect relative total energy in the different acoustic sources and q(d|s) may be updated to be the weighted histogram given by weighting the directions D(f,n) according to weights Xs′(f,n), see par. [0183]); perform blind source separation on the speech observation signal according to the second separation matrix until a separation signal frequency vector obtained by the blind source separation satisfies the preset condition (Steps 422-428 of the iteration stage 420 are iterated for a number of times, e.g. for a certain number of iterations (either predefined or dynamically defined), until one or more predefined convergence conditions is(are) satisfied, see par. [0184]); and take the separation signal frequency vector obtained as the first separation signal frequency vector (Once the iterations are finished, the method may then proceed to stage 430 where values of the model parameters q(s), q(d|s), and q(f,n|s) available after the iteration stage 420 are used to generate, for each source of interest, a respective mask for identifying contributions from the source to the characteristics X, see par. [0185]).
Regarding claim 14 Wingate teaches the electronic apparatus according to claim 9, wherein the at least one processor is configured to: determine a variance term of a probability density function of a sound source corresponding to the speech observation signal ( a directional histogram P(d|n) is formed representing the directions from which the different frequency components at time frame n originated from, see par. [0133]; Another approach is to consider the collection of all directional histograms over time and analyze which directions tend to increase or decrease in weight together. One way to do this is to compute the sample covariance or correlation matrix of these histograms, see par. [0136]); take the second pre-separation signal as a pilot signal of the variance term of the probability density function of the sound source to obtain the variance term of the probability density function of the sound source into which the pilot signal is introduced; perform blind source separation on the speech observation signal according to a first separation matrix to obtain an initial separation signal frequency vector (NN NTF is based on recognition that the NTF method for acoustic source separation described above can be viewed as a composite model in which each acoustic source is modeled via an NMF decomposition and these sources are combined according to an outer model that takes into account direction, itself a form of NMF, see par. [0142]); determine a second separation signal frequency vector according to the initial separation signal frequency vector, the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix (to that end, e.g. q(s) may be updated to reflect relative total energy in the different acoustic sources and q(d|s) may be updated to be the weighted histogram given by weighting the directions D(f,n) according to weights Xs′(f,n), see par. [0183]); and determine the second source speech signal according to the second separation signal frequency vector (the source separation method 400 may begin with an initialization stage 410. Stage 410 may include several initialization steps, at least some of which may occur in any order, see par. [0170]).
Regarding claim 15 Wingate teaches the electronic apparatus according to claim 14, wherein the at least one processor is configured to:
take the initial separation signal frequency vector as the second separation signal frequency vector, in case that the initial separation signal frequency vector satisfies a preset condition (the source separation method 400 may begin with an initialization stage 410. Stage 410 may include several initialization steps, at least some of which may occur in any order, see par. [0170]); update a reference term according to the first separation matrix and acquiring an updated reference term, in case that the initial separation signal frequency vector does not satisfy the preset condition, wherein the reference term comprises the variance term of the probability density function of the sound source into which the pilot signal is introduced, and the first separation matrix is related to the initial reference term (the quantities M.sub.s(f,n) may be viewed as soft masks because their value in each time-frequency bin is a number between zero and one, inclusive. In other implementations, one may modify the mask, such as by applying a threshold to it to produce a hard mask, which only takes values zero and one, see par. [0186]; In step 428 of the iteration stage 420, which, again, may be performed substantially the same for both, basic NTF and NN NTF, approaches, other model parameters may be updated., see par. [0183]); and determine a second separation matrix according to the updated reference term (to that end, e.g. q(s) may be updated to reflect relative total energy in the different acoustic sources and q(d|s) may be updated to be the weighted histogram given by weighting the directions D(f,n) according to weights Xs′(f,n), see par. [0183]); perform blind source separation on the speech observation signal according to the second separation matrix until a separation signal frequency vector obtained by the blind source separation satisfies the preset condition (Steps 422-428 of the iteration stage 420 are iterated for a number of times, e.g. for a certain number of iterations (either predefined or dynamically defined), until one or more predefined convergence conditions is(are) satisfied, see par. [0184]); and take the separation signal frequency vector obtained as the second separation signal frequency vector (Once the iterations are finished, the method may then proceed to stage 430 where values of the model parameters q(s), q(d|s), and q(f,n|s) available after the iteration stage 420 are used to generate, for each source of interest, a respective mask for identifying contributions from the source to the characteristics X, see par. [0185]).
Regarding claim 18 Wingate teaches a vehicle, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement steps in the speech signal processing method according to claim 1 (an audio signal acquisition device integrated in a vehicle, see par. [0086]).
Claim(s) 16 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Markovic U.S. PAP2018/0301160 A1, in view of Lim KR 20110126277 A1, further in view of Yan WO 2019/094562 A1.
Regarding claim 16 Markovic teaches: a processor (processor, see claim 1); and a memory for storing instructions executable by the processor (memory, see claim 1); wherein the processor is configured to: acquire a speech observation signal collected by a speech collection device (plurality of mixture signals, see par. [0058]); and perform blind source separation on the speech observation signal according to the first pre-separation signal to obtain a first source speech signal of the sound source of the first pre-separation signal (a first blind source separator 205A based on a first blind source separation technique or algorithm, see par. [0059]); and perform blind source separation on the speech observation signal according to the second pre-separation signal to obtain a second source speech signal of the sound source of the second pre-separation signal ( a second blind source 205N separator based on a second blind source separation technique or algorithm different to the first blind source separation technique, see par. [0059]).
However Markovich does not teach pre-separating the speech observation signal based on distance to obtain a first pre-separation signal and a second pre-separation signal, wherein a first distance between a sound source of the first pre-separation signal and the speech collection device is different from a second distance between a sound source of the second pre-separation signal and the speech collection device.
IN the same field of endeavor Lim teaches an apparatus and a method for improving the sound quality of a portable terminal of the present invention. In particular, by using two microphones, signals generated from different distances are separated to remove noise, and thus, together with a voice signal of a user in a conventional portable terminal. An apparatus and method for removing ambient noise generated., see par. [0001].
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention with the teachings of Lim for the benefit of improving the sound quality of a portable terminal, see par. [0001].
However Markovic in view of Lim does not teach an earphone, comprising the above steps.
IN the same field of endeavor Yan teaches he sound acquiring computer 120 can be an element of a hearing aid device. Therefore, the independent audio source signals can be filtered based on a users desire to listen to a signal source and disregard other signal sources, see par. [0028].
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention with the teachings of Yan for the benefit of allowing an independent audio source signals can be filtered based on a user’s desire to listen to a signal source and disregard other signal sources, see par. [0028].
Regarding claim 17 Markovic teaches: a processor (processor, see claim 1); and a memory for storing instructions executable by the processor (memory, see claim 1); wherein the processor is configured to implement steps in the speech signal processing method according to claim 1.
However Markovic does not teach a hearing aide, comprising the above steps.
IN the same field of endeavor Yan teaches he sound acquiring computer 120 can be an element of a hearing aid device. Therefore, the independent audio source signals can be filtered based on a users desire to listen to a signal source and disregard other signal sources, see par. [0028].
It would have been obvious to one of ordinary skill in the art to combine the Markovic invention with the teachings of Yan for the benefit of allowing an independent audio source signals can be filtered based on a user’s desire to listen to a signal source and disregard other signal sources, see par. [0028].
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 at 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