DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 7/6/2026 has been entered.
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 Amendment
This communication is responsive to the applicant’s response dated 6/17/2026. The applicant amended claims 2, 7, 10, 16, and 21. Additionally, claims 6, 15, and 20 have been cancelled.
Response to Arguments
Applicant's arguments with respect to 35 U.S.C. 101 (See Remarks, pg. 8, line 12 – pg. 10, line 10) filed 6/17/2026 have been fully considered but they are not persuasive.
Regarding independent claim 2, the applicant argues that a human cannot process such large amount of data and have a high processing speed and therefore cannot be a mental process. The examiner respectfully disagrees. The claim language does not go into detail about how specifically the audio is being segmented. A human can segment audio in a timeline based off time stamps in the mind or with a pen and paper. Additionally, a human can cluster audio based off time stamps in a conversation of when certain events took place. Currently, under the BRI, the claims are grouping audio based off mathematical calculations. Next, the applicant argues that the claims provide a practical application (technical improvement) because the continuous updating reduces the impact of a noise point on the cluster centers and therefore increase accuracy. The examiner fails to see how the continuous updating is related to an improvement when the applicant isn’t showing what this information is being used for. Lastly, the applicant argues that a terminal or server are not well known and routine. In particular, the applicant cites the remarks regarding the prior art rejection. However, there is no mention of the terminal or server in that section. The applicant’s arguments are not persuasive. The applicant is encouraged to go into detail of what are they doing with information that is being gathered. Is this information being used to train/improve a model or processing audio? Providing this type of information in the claim language can help show a practical application to help overcome the rejection. Therefore, the 35 U.S.C. 101 rejection is maintained.
Lastly, in the previous round of prosecution, claim 12 was viewed as a dependent claim of independent claim 1. However, upon further consideration, the examiner views claim 12 to be an independent claim. Claim 12 is simply including features from claim 1 rather than further limiting claim 1. Therefore, claim 12 is now also being rejected under 35 U.S.C. 101.
Applicant's arguments with respect to 35 U.S.C. 103 (see Remarks, pg. 10, line 11 – pg. 13, line 26) filed 6/17/2026 have been fully considered but they are not persuasive.
The applicant has rolled up claim 6 into independent claims 2 and 10. The applicant argues that Meng fails to teach “wherein the updating the second cluster center of the first set to obtain the first cluster center of the first set comprises: determining one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value; and determining the first cluster center of the first set according to the one or more second target segments in the first set”. The examiner respectfully disagrees. The examiner has provided additional citations to support his position. The applicant argues that Meng fails to disclose anything regarding a target segment in the data set whose feature information has a similarity degree that is greater than or equal to a threshold value with the clustering center of the data set. The examiner believes Meng teaches the target segments in paragraph [0045] “In S104, the multiple data to be clustered are clustered according to the clustering center to obtain target clusters”. Here the examiner interprets the target clusters as the target segments which are based on clustering centers as recited in the claim language. In terms of feature information having similarity based off a threshold value, the examiner believes Meng teaches this in paragraph [0065] “under the circumstance that the exact matching information of multiple data to be clustered is determined to be the same, the multiple data to be clustered may further be classified based on whether the fuzzy matching information is similar or not (for example, whether a distance between pieces of fuzzy matching information is smaller than or equal to a preset threshold or not)”. Here the examiner interprets the fuzzy matching information as the feature information which is being determined to be similar based off a threshold. This information is used in updating as shown in paragraph [0031] ““The basic idea is that clustering is performing of taking k points in space as initial clustering centers, objects nearest to the clustering centers are classified and a value of each clustering center is updated gradually through an iteration algorithm until a satisfactory clustering result is obtained”. Therefore, the amended limitations are met by Meng and the 35 U.S.C. 103 rejection is maintained for independent claims 2 and 10. Their respective dependent claims also remain rejected. Lastly, Independent claim 1 and 12 also remain rejected for the same reasons cited for claims 2 and 10.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 2-3, 5, 7-8, 10-12, 14, 16-17, 19, and 21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Independent claim 2 recites, “performing a segmenting processing on an audio signal to obtain multiple audio segments”, “performing a clustering processing on the multiple audio segments according to feature information of each audio segment in the multiple audio segments to obtain one or more first sets”, “determining a first cluster center of each first set according to the feature information of the audio segment comprised in each first set”, “performing the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain one or more second sets, wherein audio segments in a same second set corresponding to a same role label”, “determining a second cluster center of the first set according to the feature information of the audio segment comprised in the first set”, “updating the second cluster center of the first set to obtain the first cluster center of the first set”, “determining one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value”, and “determining the first cluster center of the first set according to the one or more second target segments in the first set”.
The limitation of segmenting an audio signal, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “segmenting” in the context of this claim encompasses breaking down audio which a human can do in the mind. Next, the limitation of clustering audio segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “clustering” in the context of this claim encompasses grouping audio which a human can do in the mind. Next, the limitation of determining cluster center, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining” in the context of this claim encompasses determining an average which a human can do in the mind or with a pen and paper. Next, the limitation of clustering on audio segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “clustering” in the context of this claim encompasses grouping audio which a human can do in the mind. Next, the limitation of determining a second cluster center, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining” in the context of this claim encompasses determining a representative audio segment, which a human can do in the mind. Next, the limitation of updating second cluster data, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “updating” in the context of this claim encompasses adjust data, which a human can do in the mind or with a pen and paper. Next, the limitation of determining target segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining” in the context of this claim encompasses classifying audio which a human can do in the mind or with a pen and paper. Lastly, the limitation of determining cluster centers based off target segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining” in the context of this claim encompasses determining a midpoint or representation portion of audio which a human can do in the mind or with pen and paper.
The judicial exception is not integrated into a practical application because the claim does not recite any additional elements to perform the recited claim or do not add a meaningful limitation to the method as they are insignificant extra-solution activity. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim is not patent eligible.
Dependent claims 3, 5, 7-8, 11, 19, and 21 are also rejected for the same reasons provided in independent claim 2 above. The dependent claim, including the further recited limitation, does not integrate the abstract idea into a practical application and the additional elements, taken individually and in combination do not contribute to an inventive concept. In other words, the dependent claim is directed to an abstract idea without significantly more.
Independent claim 10 recites, “perform a segmenting processing on an audio signal to obtain multiple audio segments”, “perform a clustering processing on the multiple audio segments according to feature information of each audio segment in the multiple audio segments to obtain one or more first sets”, “determine a first cluster center of each first set according to the feature information of the audio segment comprised in each first set”, “perform the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain one or more second sets, wherein audio segments in a same second set corresponding to a same role label”, “determine a second cluster center of the first set according to the feature information of the audio segment comprised in the first set”, and “update the second cluster center of the first set to obtain the first cluster center of the first set”, “determine one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value”, and “determine the first cluster center of the first set according to the one or more second target segments in the first set”.
The limitation of segmenting audio signals as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “a terminal or a server”, “a memory”, “a processor”, and “a computer program”, nothing in the claim precludes the step from practically being performed in the mind. For example, but for the “a terminal or a server”, “a memory”, “a processor”, and “a computer program”, “segmenting” in the context of this claim encompasses breaking down audio which a human can do in the mind. Next, the limitation of clustering audio segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting the elements listed above, nothing in the claim precludes the step from practically being performed in the mind. For example, “clustering” in the context of this claim encompasses grouping audio which a human can do in the mind. Next, the limitation of determining cluster center, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting the elements listed above, nothing in the claim precludes the step from practically being performed in the mind. For example, “determine” in the context of this claim encompasses determining an average which a human can do in the mind or with a pen and paper. Next, the limitation of performing clustering of multiple audio segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting the elements listed above, nothing in the claim precludes the step from practically being performed in the mind. For example, “clustering” in the context of this claim encompasses grouping audio which a human can do in the mind. Next, the limitation of determining a second cluster center, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determine” in the context of this claim encompasses determining a representative audio segment, which a human can do in the mind. Next, the limitation of updating second cluster data, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “update” in the context of this claim encompasses adjust data, which a human can do in the mind or with a pen and paper. Next, the limitation of determining target segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining” in the context of this claim encompasses classifying audio which a human can do in the mind or with a pen and paper. Lastly, the limitation of determining cluster centers based off target segments, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining” in the context of this claim encompasses determining a midpoint or representation portion of audio which a human can do in the mind or with pen and paper.
The judicial exception is not integrated into a practical application. In particular, the claim only recites the additional elements, “a terminal or a server”, “a memory”, “a processor”, and “a computer program” to perform the recited limitations. These elements in these steps are recited at a high-level of generality such that is amounts no more than mere instructions to apply the exception using generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of using “a terminal or a server”, “a memory”, “a processor”, and “a computer program” to perform the recited limitations amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Dependent claims 14, 16-17 are also rejected for the same reasons provided in independent claim 10 above. The dependent claim, including the further recited limitation, does not integrate the abstract idea into a practical application and the additional elements, taken individually and in combination do not contribute to an inventive concept. In other words, the dependent claim is directed to an abstract idea without significantly more.
Independent claim 12 recites, “send an audio signal of multiple roles in a conference to the server” and “send the audio signal of multiple roles in the conference to the terminal”.
Regarding these limitations, of sending audio signals, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting a “server” and “terminal” nothing in the claim precludes the step from practically being performed in the mind. For example, “send” in the context of this claim encompasses sending audio which a human can do in the mind.
The judicial exception is not integrated into a practical application. In particular, the claim only recites the additional elements, “a terminal or a server”, to perform the recited limitations. These elements in these steps are recited at a high-level of generality such that is amounts no more than mere instructions to apply the exception using generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of using “a terminal or a server” to perform the recited limitations amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim 12 is rejected under 35 U.S.C. 102(a)(1) as being anticipated by Boxwell et al. US 10440325 B1 (hereinafter Boxwell).
Regarding independent claim 12, Boxwell teaches a conference system, comprising a terminal and a server; wherein the terminal and the server are communicatively connected; the terminal is configured to send an audio signal of multiple roles in a conference to the server or the server is configured to send the audio signal of multiple roles in the conference to the terminal, and correspondingly, the server or the terminal is configured to perform the method according to claim 1 (FIG. 1, [Column 6, line 19-33] “The users 130 may be individuals which are associated with a respective participant device. For example, the users 130 may be employees of one or more companies which are participating in a video conference via the video conference system 100… The users 130 may have different roles within the video conference, such as leader, listener, viewer, etc., all of which may be considered a “participant” role as used herein”)
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 1 is rejected under 35 U.S.C. 103 as being unpatentable over Yan in view of Meng in view of Li, Y.et al. (2016, July). Speaker role clustering using turn features and maximum inter-cluster distances. In 2016 International Conference on Audio, Language and Image Processing (ICALIP) (pp. 482-486). IEEE. (Year: 2016).
Regarding independent claim 1, Yan teaches a role processing method in a conference scene, applied to a terminal or a server, and comprising:
receiving an audio signal of multiple roles in a conference ([p. 2, paragraph 5] “obtaining the voice segment with human voice”);
performing a segmenting processing on the audio signal to obtain multiple audio segments ([p. 2, paragraph 6] “dividing the voice segment with human voice to obtain a plurality of voice sub-segments”);
performing a clustering processing on the multiple audio segments according to feature information of each audio segment in the multiple audio segments to obtain one or more first sets ([p. 2, paragraph 8] “performing cascade clustering for the voiceprint characteristic corresponding to all the voice sub-segments”, examiner interprets voiceprint characteristics as features and output of the clustering as the set.);
calculating a first mean value of the feature information of the audio segment comprised in the first set ([p.2, paragraph 12] “performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”);
taking the first mean value as a second cluster center of the first set ([pg. 6, paragraph 1]“when performing the K-means clustering, firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre.”);
calculating a second mean value of the feature information corresponding to the one or more second target segments in the first set ([p. 2, paragraph 12] “performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”);
taking the second mean value as a first cluster center of the first set ([p. 3, paragraph 8] “a second clustering sub-module, for the first clustering result is the initial value of the Kmeans clustering for the first clustering result for the second clustering”);
Yan fails to teach determining one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value; for each audio segment in the multiple audio segments, according to the feature information of the audio segment and the first cluster center of each first set, calculating a distance between the audio segment and each first cluster center respectively; dividing an audio segment in the multiple audio segments whose distance with the first cluster center is less than or equal to a third threshold value into a second set; determining role information of multiple speakers in the audio signal according to the second set; and taking the second set as the first set, and performing a process from calculation of the first mean value to determination of the role information repeatedly
However, Meng teaches determining one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value ([0065] “the multiple data to be clustered may further be classified based on whether the fuzzy matching information is similar or not (for example, whether a distance between pieces of fuzzy matching information is smaller than or equal to a preset threshold or not)”);
for each audio segment in the multiple audio segments, according to the feature information of the audio segment and the first cluster center of each first set, calculating a distance between the audio segment and each first cluster center respectively ([0064] “after the clustering centers are determined, a distance between each of the multiple data to be clustered and each clustering center can be determined, and a clustering center at a shortest distance can be determined as the nearest center of the data to be clustered”);
dividing an audio segment in the multiple audio segments whose distance with the first cluster center is less than or equal to a third threshold value into a second set ([0083] In S405, clustered data at a distance larger than or equal to a preset distance threshold away from the clustering center is removed from the target clusters.);
Yan in view of Meng are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques of voice processing of Yan with the technique of calculating a distance between cluster centers taught by Meng in order to improve techniques of data clustering (see Meng [0003]).
Yan in view of Meng fails to teach determining role information of multiple speakers in the audio signal according to the second set; and taking the second set as the first set, and performing a process from calculation of the first mean value to determination of the role information repeatedly
However, Li teaches determining role information of multiple speakers in the audio signal according to the second set (FIG. 1); and
taking the second set as the first set, and performing a process from calculation of the first mean value to determination of the role information repeatedly (page 2, 2nd paragraph, 2.2.1 Feature Definition D, G, N, and T)
Yan in view of Meng in view of Li are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques clustering data elements of Yan in view of Meng with the technique of determining role information taught by Li in order to improve techniques of speaker role clustering in order to obtain the number roles (see Li [Abstract]).
Claims 2-3, 5-8, 10-11, 14-17, and 19-21 are rejected under 35 U.S.C. 103 as being unpatentable over Yan in view of Meng.
Regarding claim 2, Yan teaches an audio signal processing method, applied to a terminal or a server, and comprising:
performing a segmenting processing on an audio signal to obtain multiple audio segments ([p. 2, paragraph 6] “dividing the voice segment with human voice to obtain a plurality of voice sub-segments”);
performing a clustering processing on the multiple audio segments according to feature information of each audio segment in the multiple audio segments to obtain one or more first sets ([p. 2, paragraph 8] “performing cascade clustering for the voiceprint characteristic corresponding to all the voice sub-segments”, examiner interprets voiceprint characteristics as features and output of the clustering as the set);
determining a first cluster center of each first set according to the feature information of the audio segment comprised in each first set ([p. 6, paragraph 1] “when performing the K-means clustering, firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre. In this embodiment, the number K of the clustering is the first clustering result comprises the category number, each initial clustering centre is selected from the first clustering result.”); and
performing the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain one or more second sets, wherein audio segments in a same second set corresponding to a same role label ([p. 5, paragraph 13] “S32 to the first clustering result is the initial value of the Kmeans clustering for the first clustering result for the second clustering result, obtaining the second clustering result”;[p. 2, paragraph 8] “obtaining the speaker label corresponding to each voice sub-segment”, examiner interprets speaker label as role information)
Yan fails to teach wherein the determining the first cluster center of each first set according to the feature information of the audio segment comprised in each first set comprises: determining a second cluster center of the first set according to the feature information of the audio segment comprised in the first set; and updating the second cluster center of the first set to obtain the first cluster center of the first set; wherein the updating the second cluster center of the first set to obtain the first cluster center of the first set comprises: determining one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value; and determining the first cluster center of the first set according to the one or more second target segments in the first set.
However, Meng teaches wherein the determining the first cluster center of each first set according to the feature information of the audio segment comprised in each first set comprises: determining a second cluster center of the first set according to the feature information of the audio segment comprised in the first set (FIG. 3, S301 [0012] determine a clustering center according to the amount of the data to be clustered in each of the multiple data sets; FIG. 6, 230-232; [0104] “a data set arrangement sub-portion 231, configured to arrange the multiple data sets according to a sequence from large to small amounts of the data to be clustered in the multiple data sets”, here the examiner interprets the sub-portion to be the second cluster); and
updating the second cluster center of the first set to obtain the first cluster center of the first set (FIG. 3, S302 [0072] “In S302, the clustering center is updated according to a calculation result about the nearest center”; FIG. 6, 242, [0108] “a clustering center updating sub-portion 242, configured to update the clustering center according to a calculation result about the nearest center”).
wherein the updating the second cluster center of the first set to obtain the first cluster center of the first set comprises ([0031] “The basic idea is that clustering is performing of taking k points in space as initial clustering centers, objects nearest to the clustering centers are classified and a value of each clustering center is updated gradually through an iteration algorithm until a satisfactory clustering result is obtained”): determining one or more second target segments in the first set according to the second cluster center of the first set ([0045] In S104, the multiple data to be clustered are clustered according to the clustering center to obtain target clusters.), wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value ([0065] “under the circumstance that the exact matching information of multiple data to be clustered is determined to be the same, the multiple data to be clustered may further be classified based on whether the fuzzy matching information is similar or not (for example, whether a distance between pieces of fuzzy matching information is smaller than or equal to a preset threshold or not)”); and determining the first cluster center of the first set according to the one or more second target segments in the first set ([0057] “after the first N arranged data sets are determined, the clustering center of each set in the N data sets can be determined, and then the N clustering centers can be determined as the clustering centers for clustering of the multiple data to be clustered”).
Yan in view of Meng are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques of voice processing of Yan with the technique of calculating a distance between cluster centers taught by Meng in order to improve techniques of data clustering (see Meng [0003]).
Regarding claim 3, Yan teaches all of the limitations of claim 2, upon which claim 3 depends.
Additionally, Yan teaches taking feature information corresponding to the first target segment as the first cluster center of the first set ([p.3, paragraph 5] “voiceprint feature clustering module, for performing cascade clustering for the voiceprint feature corresponding to all the voice sub-fragment, obtaining the speaker tag corresponding to each voice sub-fragment;” [p. 2, paragraph 13] “the iteration stopping condition is as follows: the cluster central point change rate of partial cluster cluster in the plurality of cluster clusters does not exceed the set range”).
Yan fails to teach determining the first cluster center of each first set according to the feature information of the audio segment comprised in each first set comprises: determining a first target segment in the first set, wherein a sum of similarity degree scores between the first target segment and other audio segments in the first set is greater than a first threshold value
However, Meng teaches determining the first cluster center of each first set according to the feature information of the audio segment comprised in each first set comprises: determining a first target segment in the first set, wherein a sum of similarity degree scores between the first target segment and other audio segments in the first set is greater than a first threshold value ([0065] “the multiple data to be clustered may further be classified based on whether the fuzzy matching information is similar or not (for example, whether a distance between pieces of fuzzy matching information is smaller than or equal to a preset threshold or not)”);
Yan in view of Meng are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques voice processing of Yan with the technique of determining target segment similarity taught by Meng in order to improve techniques of data clustering (see Meng [0003]).
Regarding claim 5, Yan in view of Meng teaches all of the limitations of claim 2, upon which claim 5 depends.
Additionally, Yan teaches wherein the determining the second cluster center of the first set according to the feature information of the audio segment comprised in the first set comprises: calculating a first mean value of the feature information of the audio segment comprised in the first set ([p. 6, paragraph 1]“when performing the K-means clustering….”);
and taking the first mean value as the second cluster center of the first set ([p. 6, paragraph 1] “firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre… the number K of the clustering is the first clustering result comprises the category number, each initial clustering centre is selected from the first clustering result. one to-be-clustering centre of the K means clustering is selected from one type of the first clustering result”; [pg. 2, paragraph 12]“performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”)
Regarding claim 7, Yan in view of Meng teaches all of the limitations of claim 2, upon which claim 7 depends.
Additionally, Yan teaches wherein the determining the first cluster center of the first set according to the one or more second target segments in the first set comprises: calculating a second mean value of the feature information corresponding to the one or more second target segments in the first set ([p. 6, paragraph 1]“when performing the K-means clustering, firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre”; [pg. 6, paragraph 15] “for the first clustering result is the initial value of the Kmeans clustering for the first clustering result for the second clustering, obtaining the second clustering result; wherein the Early Stop mechanism, the Kmeans cluster satisfies the iteration stop condition”); and
taking the second mean value as the first cluster center of the first set ([p. 6, paragraph 3] “when setting the cluster number, setting 10 cluster cluster, by Early Stop mechanism, the change rate of cluster center point of 3 cluster cluster in the cluster cluster is not more than the set range, can stop the iterative calculation, finishing the second clustering”; [pg. 6, paragraph 5] “the first clustering result for the second clustering, also can adopt Kmeans + +”).
Regarding claim 8, Yan teaches all of the limitations of claim 2, upon which claim 8 depends.
Yan fails to teach wherein the performing the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain the one or more second sets comprises: for each audio segment in the multiple audio segments, according to the feature information of the audio segment and the first cluster center of each first set, calculating a distance between the audio segment and each first cluster center respectively; and dividing an audio segment in the multiple audio segments whose distance with the first cluster center is less than or equal to a third threshold value into a second set.
However, Meng teaches wherein the performing the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain the one or more second sets comprises: for each audio segment in the multiple audio segments, according to the feature information of the audio segment and the first cluster center of each first set, calculating a distance between the audio segment and each first cluster center respectively ([0064] “after the clustering centers are determined, a distance between each of the multiple data to be clustered and each clustering center can be determined, and a clustering center at a shortest distance can be determined as the nearest center of the data to be clustered”); and
dividing an audio segment in the multiple audio segments whose distance with the first cluster center is less than or equal to a third threshold value into a second set ([0083] In S405, clustered data at a distance larger than or equal to a preset distance threshold away from the clustering center is removed from the target clusters.).
Yan in view of Meng are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques voice processing of Yan with the technique of calculating distances between cluster centers taught by Meng in order to improve techniques of data clustering (see Meng [0003]).
Regarding independent claim 10, Yan teaches an electronic device, which is a terminal or a server, and comprises:
a memory (Fig. 5, 1103);
a processor (Fig. 5, 1101); and
a computer program; wherein the computer program is stored in the memory the processor, when executing the computer program ([p.7, paragraph 9], “the first memory 1103 can store various programs”), is configured to:
perform a segmenting processing on an audio signal to obtain multiple audio segments ([p. 2, paragraph 6] “dividing the voice segment with human voice to obtain a plurality of voice sub-segments”););
perform a clustering processing on the multiple audio segments according to feature information of each audio segment in the multiple audio segments to obtain one or more first sets ([p. 2, paragraph 8] “performing cascade clustering for the voiceprint characteristic corresponding to all the voice sub-segments”, examiner interprets voiceprint characteristics as features and output of the clustering as the set);
determine a first cluster center of each first set according to the feature information of the audio segment comprised in each first set ([p. 6, paragraph 1] “when performing the K-means clustering, firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre. In this embodiment, the number K of the clustering is the first clustering result comprises the category number, each initial clustering centre is selected from the first clustering result.”;); and
perform the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain one or more second sets, wherein audio segments in a same second set corresponding to a same role label ([p. 5, paragraph 13] “S32 to the first clustering result is the initial value of the Kmeans clustering for the first clustering result for the second clustering result, obtaining the second clustering result”;[p. 2, paragraph 8] “obtaining the speaker label corresponding to each voice sub-segment”, examiner interprets speaker label as role information).
Yan fails to teach wherein the determining the first cluster center of each first set according to the feature information of the audio segment comprised in each first set comprises: determining a second cluster center of the first set according to the feature information of the audio segment comprised in the first set; and updating the second cluster center of the first set to obtain the first cluster center of the first set; wherein the processor, when updating the second cluster center of the first set to obtain the first cluster center of the first set, is configured to: determine one or more second target segments in the first set according to the second cluster center of the first set, wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value; and determine the first cluster center of the first set according to the one or more second target segments in the first set.
However, Meng teaches wherein the processor is configured to: determine a second cluster center of the first set according to the feature information of the audio segment comprised in the first set (FIG. 3, S301 [0012] determine a clustering center according to the amount of the data to be clustered in each of the multiple data sets; FIG. 6, 230-232; [0104] “a data set arrangement sub-portion 231, configured to arrange the multiple data sets according to a sequence from large to small amounts of the data to be clustered in the multiple data sets”, here the examiner interprets the sub-portion to be the second cluster); and
update the second cluster center of the first set to obtain the first cluster center of the first set (FIG. 3, S302 [0072] “In S302, the clustering center is updated according to a calculation result about the nearest center”; FIG. 6, 242, [0108] “a clustering center updating sub-portion 242, configured to update the clustering center according to a calculation result about the nearest center”).
wherein the processor, when updating the second cluster center of the first set to obtain the first cluster center of the first set ([0031] “The basic idea is that clustering is performing of taking k points in space as initial clustering centers, objects nearest to the clustering centers are classified and a value of each clustering center is updated gradually through an iteration algorithm until a satisfactory clustering result is obtained”), is configured to: determine one or more second target segments in the first set according to the second cluster center of the first set ([0045] “In S104, the multiple data to be clustered are clustered according to the clustering center to obtain target clusters”), wherein a similarity degree between feature information corresponding to the second target segments and the second cluster center of the first set is greater than or equal to a second threshold value ([0065] “under the circumstance that the exact matching information of multiple data to be clustered is determined to be the same, the multiple data to be clustered may further be classified based on whether the fuzzy matching information is similar or not (for example, whether a distance between pieces of fuzzy matching information is smaller than or equal to a preset threshold or not)”); and determine the first cluster center of the first set according to the one or more second target segments in the first set ([0057] “after the first N arranged data sets are determined, the clustering center of each set in the N data sets can be determined, and then the N clustering centers can be determined as the clustering centers for clustering of the multiple data to be clustered”)
Yan in view of Meng are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques of voice processing of Yan with the technique of calculating a distance between cluster centers taught by Meng in order to improve techniques of data clustering (see Meng [0003]).
Regarding claim 14, Yan in view of Meng teaches all of the limitations of claim 10, upon which claim 14 depends.
Additionally, Yan teaches calculate a first mean value of the feature information of the audio segment comprised in the first set ([p.2, paragraph 12] “performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”); and
take the first mean value as the second cluster center of the first set ([pg. 6, paragraph 1]“when performing the K-means clustering, firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre.”)
Regarding claim 16, Yan in view of Meng teaches all of the limitations of claim 10, upon which claim 16 depends.
Additionally, Yan teaches wherein the processor, when determining the first cluster center of the first set according to the one or more second target segments in the first set, is configured to: calculate a second mean value of the feature information corresponding to the one or more second target segments in the first set ([p. 2, paragraph 12] “performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”); and
take the second mean value as the first cluster center of the first set ([p. 3, paragraph 8] “a second clustering sub-module, for the first clustering result is the initial value of the Kmeans clustering for the first clustering result for the second clustering”).
Regarding claim 17, Yan teaches all of the limitations of claim 10, upon which claim 17 depends.
Yan fails to teach wherein the processor, when performing the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain the one or more second sets, is configured to: for each audio segment in the multiple audio segments, according to the feature information of the audio segment and the first cluster center of each first set, calculate a distance between the audio segment and each first cluster center respectively; and divide an audio segment in the multiple audio segments whose distance with the first cluster center is less than or equal to a third threshold value into a second set.
However, Meng teaches wherein the processor, when performing the clustering processing on the multiple audio segments according to the first cluster center of each first set to obtain the one or more second sets, is configured to: for each audio segment in the multiple audio segments, according to the feature information of the audio segment and the first cluster center of each first set, calculate a distance between the audio segment and each first cluster center respectively ([0064] “after the clustering centers are determined, a distance between each of the multiple data to be clustered and each clustering center can be determined, and a clustering center at a shortest distance can be determined as the nearest center of the data to be clustered”); and
divide an audio segment in the multiple audio segments whose distance with the first cluster center is less than or equal to a third threshold value into a second set ([0083] In S405, clustered data at a distance larger than or equal to a preset distance threshold away from the clustering center is removed from the target clusters.).
Yan in view of Meng are considered to be analogous to the claimed invention because both are the same field of clustering data. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the techniques voice processing of Yan with the technique of calculating the distance between audio segments and clusters taught by Meng in order to improve techniques of data clustering (see Meng [0003]).
Regarding claim 19, Yan in view of Meng teaches all of the limitations of claim 11, upon which claim 19 depends.
Additionally, Yan teaches wherein the processor is configured to: calculate a first mean value of the feature information of the audio segment comprised in the first set ([p.2, paragraph 12] “performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”); and
take the first mean value as the second cluster center of the first set ([pg. 6, paragraph 1]“when performing the K-means clustering, firstly giving the number K of the clustering, then initially randomly giving K to-be-clustering centre”).
Regarding claim 21, Yan in view of Meng teaches all of the limitations of claim 11, upon which claim 21 depends.
Additionally, Yan teaches wherein the processor, when determining the first cluster center of the first set according to the one or more second target segments in the first set, is configured to: calculate a second mean value of the feature information corresponding to the one or more second target segments in the first set ([p. 2, paragraph 12] “performing the second clustering to the first clustering result with the initial value of the first clustering result as the Kmeans clustering to obtain the second clustering result”); and
take the second mean value as the first cluster center of the first set ([p. 3, paragraph 8] “a second clustering sub-module, for the first clustering result is the initial value of the Kmeans clustering for the first clustering result for the second clustering”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Khoury et al. (US 11842748 B2) teaches methods, systems, and apparatuses for audio event detection, where the determination of a type of sound data is made at the cluster level rather than at the frame level. The techniques provided are thus more robust to the local behavior of features of an audio signal or audio recording. The audio event detection is performed by using Gaussian mixture models (GMMs) to classify each cluster or by extracting an i-vector from each cluster. Each cluster may be classified based on an i-vector classification using a support vector machine or probabilistic linear discriminant analysis. The audio event detection significantly reduces potential smoothing error and avoids any dependency on accurate window-size tuning. Segmentation may be performed using a generalized likelihood ratio and a Bayesian information criterion, and the segments may be clustered using hierarchical agglomerative clustering. Audio frames may be clustered using K-means and GMMs.
Wexler et al. (US 20210337307 A1) teaches a wearable device may include an image sensor configured to capture a plurality of images from an environment, a microphone configured to capture sounds from the environment, and at least one processor. The at least one processor may be programmed to receive audio signals representative of the sounds captured by the at least one microphone, and receive a first image including a representation of a first individual from among the plurality of images captured by the image sensor. The at least one processor may also be programmed to obtain a first audio segment from the audio signals using the first image. The first audio segment may include a first portion of the audio signals in which the first individual is speaking. The at least one processor may also be programmed to receive a second image including a representation of a second individual from among the plurality of images captured by the image sensor, and obtain a second audio segment from the audio signals using the second image. The second audio segment may include a second portion of the audio signals in which the second individual is speaking. The at least one processor may also be programmed to receive a third image including a representation of the first individual from among the plurality of images captured by the image sensor, and using the third image, obtain a third audio segment from the audio signals. The audio segment may include a third portion of the audio signals in which the first individual is speaking. The at least one processor may also associate the first and third audio segments with the first individual and associate the second audio segment with the second individual.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZEESHAN SHAIKH whose telephone number is (703)756-1730. The examiner can normally be reached Monday-Friday 7:30AM-5:00PM.
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, Richemond Dorvil can be reached at (571) 272-7602. 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.
/ZEESHAN MAHMOOD SHAIKH/Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658
