DETAILED ACTION
This communication is in response to the Amendments and Arguments filed on 03/18/2026.
Claim(s) 1-18 are pending and have been examined. Hence, this action has been made FINAL.
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 and Amendments
Amendments to the claims by the Applicant have been considered and addressed below.
With respect to the 35 USC § 101, 102/103 rejections, the Applicant provides several arguments in which the Examiner will respond accordingly, below.
35 USC § 101 rejection(s)
Arguments on pages 6-9 of the remarks filed on 03/18/2026.
Examiner’s Response to Arguments:
Applicant’s arguments with respect to independent claim 1 along with the amendments have been fully considered and are persuasive. The 35 USC § 101 (abstract idea) rejections of independent claim 1 and its dependent claims have been withdrawn.
However, the Examiner notes that independent claims 5 (no significant amendment) and 6 (not amended) and their dependent claims still present 35 USC § 101 (abstract idea) issues.
For more details, please refer to updated 35 U.S.C. § 101 rejections for claims 5-12, and 15-18, below.
35 USC § 102/103 rejection(s)
Arguments on pages 10-12 of the remarks filed on 03/18/2026.
Examiner’s Response to Arguments:
Applicant’s arguments with respect to independent claim(s) 1 under 35 U.S.C. § 102 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.
Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Yoshioka et al. (US 20200349230 A1) and further in view of Chang et al. (US 20210314700 A1).
For more details, please refer to updated 35 U.S.C. § 103 rejections for claims 1-18, below.
Specification
The lengthy specification has not been checked to the extent necessary to determine the presence of all possible minor errors. Applicant’s cooperation is requested in correcting any errors of which applicant may become aware in the specification.
Claim Objections
Claim 6 objected to because of the following informalities: (Currently Amended) status should read (Previously Presented). Appropriate correction is required.
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 6, 10-12 and 17-18 rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because the claims disclose “signal processing program” in the preamble directing the claim(s) towards a software/data structure or “software per se.”
Claim(s) 5-12, and 15-18 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. More specifically directed to the abstract idea grouping of: mental process and/or certain methods of organizing human activity.
The independent claim(s) 5-6 recite(s):
5. (Currently Amended) A signal processing method executed by a signal processing device, the signal processing method comprising:
6. (Currently Amended) A signal processing program for causing a computer to execute:
generating, from an observation signal, an enhancement signal in which a voice of a speaker is enhanced;
adding the observation signal to the enhancement signal; and
performing speech recognition on the enhancement signal to which the observation signal is added in the adding step.
This reads on a human (e.g., mentally and/or using pen and paper):
(i.e., human – adult) Repeating out loud speech spoken by another human (e.g., child);
Adding words used by the child to his/her utterance;
Writing down the utterance.
This judicial exception is not integrated into a practical application because for example: claims 5 and 13-14 recite “a signal processing device”. As an example, in [0067] of the as filed specification, it is disclosed: “Fig. 9 is a diagram illustrating an example of a computer in which a program is executed to implement the signal processing device 10. A computer 1000 includes a memory 1010 and a CPU 1020, for example. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected to each other by a bus 1080.”. Therefore, a general-purpose computer or computing device is described and mainly used as an application thereof. Accordingly, these additional elements do not integrate the abstract idea into a practical idea because it does not impose any meaningful limits on practicing the abstract idea.
The claim(s) does/do 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 computer is listed as a general computing device as noted. The claim is not patent eligible.
With respect to claims 7, and 10, the claim(s) recite:
7, and 10. (Original) The signal processing device/method/program according to claims 5, and 6,
wherein the observation signal is an audio signal recorded by a single microphone
This reads on a human (e.g., mentally and/or using pen and paper):
Receiving an utterance (spoken signal) by another human
This judicial exception is not integrated into a practical application because for example: claims 2, 7, and 10 recite “a microphone”. As an example, in [0067] of the as filed specification, it is disclosed: “Fig. 9 is a diagram illustrating an example of a computer in which a program is executed to implement the signal processing device 10. A computer 1000 includes a memory 1010 and a CPU 1020, for example. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected to each other by a bus 1080.”. Therefore, a general-purpose computer or computing device is described and mainly used as an application thereof. Accordingly, these additional elements do not integrate the abstract idea into a practical idea because it does not impose any meaningful limits on practicing the abstract idea.
The claim(s) does/do 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 computer is listed as a general computing device as noted. The claim is not patent eligible.
With respect to claims 8, and 11, the claim(s) recite:
8, and 11. (Currently Amended) The signal processing device/method/program according to claims 5, and 6,
wherein the addition unit adjusts a weight of an observation signal to be added to the enhancement signal according to a ratio of a noise signal included in the observation signal
This reads on a human (e.g., mentally and/or using pen and paper):
Assigning a value (e.g., importance) to a word/sentence in the received utterance (spoken signal) by another human compared to other noises in the background
No additional limitations are present.
With respect to claims 9, and 12, the claim(s) recite:
9, and 12. (Original) The signal processing device/method/program according to claims 5, and 6,
wherein the addition unit weights only an observation signal to be added to the enhancement signal, or weights both the observation signal and the observation signal to be added to the enhancement signal in a relationship in which a sum of a weight of the observation signal and a weight of the observation signal to be added to the enhancement signal is 1.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein the assigning a value (e.g., importance) to a word/sentence in the received utterance (spoken signal) by another human compared to other noises in the background is based on predetermined set of rules (e.g., only applied to a part of the word/sentence in the received utterance (spoken signal) by another human)
No additional limitations are present.
With respect to claims 15, and 17, the claim(s) recite:
15, and 17. (New) The signal processing device/method/program according to claim 5, and 6,
wherein the speech recognition unit performs speech recognition and outputs a speech recognition result obtained by converting a message signal into text
This reads on a human (e.g., mentally and/or using pen and paper):
Writing down the utterance.
No additional limitations are present.
With respect to claims 16, and 18, the claim(s) recite:
16, and 18. (New) The signal processing device/method/program according to claim 5, and 6,
wherein the speech recognition unit performs speech enhancement processing using a trained deep learning model
This reads on a human (e.g., mentally and/or using pen and paper):
(i.e., human – adult) Repeating out loud speech spoken by another human (e.g., child) using a predetermined set of rules/steps (i.e., model)
No additional limitations are present.
Claim Rejections - 35 USC § 102
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 5-7, 10, 13-18 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Yoshioka et al. (US 20200349230 A1).
As to independent claim 5, Yoshioka et al. teaches:
5. (Currently Amended) A signal processing method executed by a signal processing device (see ¶ [0025 and 0028] citations as in claim 1, above. “[0025] Furthermore, the claimed subject matter may be implemented as a method, apparatus, …), the signal processing method comprising:
generating, from an observation signal, an enhancement signal in which a voice of a speaker is enhanced (see ¶ [0025 and 0028] citations as in preamble above and further ¶ [0040]: “There may be additional devices that are within audio or visual range of the meeting 100, such as a digital assistant 148 or a dedicated meeting device 150, both of which are shown on the table 130, but can be anywhere within audio range of the meeting 100. Such additional devices may be connected to the distributed meeting server 135 and have their audio streams added to the meeting instance for processing to further enhance the audio and speech-to-text processing capabilities of the meeting instance running on the meeting server 135. Such additional devices may be detected by the meeting server 135 and added to the meeting as described above or may be presented to one or more of the users as an option to add to the meeting.”
¶ [0076-0077]: “[0076] Stream synchronization module 1015 provides a multi-channel synchronized signal, {[y.sub.0(t), . . . , y.sub.M-1(t)]; t=0, 1, . . . } to a beamforming module 1020. The beamforming module 1020 functions to separate overlapping speech. Overlapping speech occurs when two people in the meeting speak at the same time. Prior to recognizing the speech and converting the speech to text, the speech is first separated into separate channels. Thus with an M-channel input, the output is N-channels, and is referred to as an N-channel beamformed signal, {[z.sub.0(t), . . . , z.sub.N-1(t)]; t=0, 1, . . . }. The stream synchronization module 1015 acts as a first fusion point, where multiple outputs are generated to retain the diversity of the input information. Where no speech overlaps, such fusion is optional. [0077] FIG. 11 is a flowchart illustrating a computer-implemented method 1100 of synchronizing multiple audio channels received from multiple distributed devices during an intelligent meeting. At operation 1110, audio signals representative of streamed speech are received from multiple distributed devices to generate multiple audio channels. A selected one of the audio channels is designated at operation 1120 as a reference channel.”
and ¶ [0079-0081]: “[0079] Method 1100 may be performed periodically to correct the timing of the remaining audio channels, such as every 30 seconds. In one embodiment, method 1100 includes further operations to correct for the global offset caused at least by different clocks in the distributed devices. At operation 1150, a global offset is determined for each of the remaining audio channels. The remaining audio channels are then corrected at operation 1160 by each corresponding remaining audio channel global offset prior to correcting each remaining audio channel for the determined difference in time. [0080] Acoustic beamforming, or simply beamforming, is a technique to enhance target speech by reducing unwanted sounds such as background noise from multi-channel audio signals. Beamforming can improve accuracy of downstream speech processing, such as speech recognition and speaker diarization. [0081] For an intelligent meeting with audio streamed from multiple distributed devices whose exact positions relative to one another are not known, traditional beamforming algorithms, such as delay-and-sum beamforming, superdirective beamforming, and differential beamforming do not work. Such algorithms rely on prior knowledge about the arrangement of microphone devices, which is not available for distributed devices.”);
adding the observation signal to the enhancement signal (see ¶ [0025, 0028, 0040, 0076-0077, and 0079-0081] citations as in limitation(s) above. [0076-0077]: “overlapping speech” [0079-0081]: “delay-and-sum beamforming” and further Fig. 9 (910, 912, 914: devices/speech signals, 930: fusion and 940: transcript) and ¶ [0069-0070]: “[0069] The meeting transcriber 925 includes a synchronization module or function in addition to a speech recognition module or function. The audio signals from the audio channels 916, 918, and 920 are first synchronized and then recognized, resulting in texts associated with each of the channels according to one embodiment. The recognition outputs are then fused (by fusion 930) or otherwise processed to generate a transcript 940. The transcript 940 may then be provided back to the users. In other embodiments, the audio signals from the audio channels 916, 918, and 920 are fused before speech recognition. The audio signal obtained after the fusion is recognized, resulting in a single version of text. In some embodiments, the transcript may be provided with very little delay. [0070] In various embodiments, the conversion of the audio signals to text that is used in conjunction with speaker identification and generation of the transcript that is diarized to identify speakers are provided by the meeting server 135. The functions performed by the meeting server 135 include the synchronization, recognition, fusion, and diarization functions. While such functions are shown in a particular order in FIG. 9, in different embodiments, the functions may be performed in varying orders. For example, fusion may be performed prior to recognition and may also be performed at various other points as described below.”
as well as Fig. 10 (1020: beamforming module, fusion points, and 1060: Hypothesis combination) and ¶ [0101]: “The output from combination module 1060 is the result of a third fusion, referred to as a late fusion, to produce text and speaker identification for generation of a speaker-attributed transcript of the meeting…”); and
performing speech recognition on the enhancement signal to which the observation signal is added by the addition unit (see Fig. 9-10 and ¶ [0025, 0028, 0040, 0076-0077, 0079-0081, and 0101] citations as in limitation(s) above. More specifically: [0076-0077]: “overlapping speech” [0079-0081]: “delay-and-sum beamforming”, Fig. 9 (910, 912, 914: devices/speech signals, 930: fusion and 940: transcript), Fig. 10 (1020: beamforming module, fusion points, and 1060: Hypothesis combination), ¶ [0070]: “In various embodiments, the conversion of the audio signals to text that is used in conjunction with speaker identification and generation of the transcript that is diarized to identify speakers are provided by the meeting server 135. […] For example, fusion may be performed prior to recognition and may also be performed at various other points as described below.” and ¶ [0101]: “The output from combination module 1060 is the result of a third fusion, referred to as a late fusion, to produce text and speaker identification for generation of a speaker-attributed transcript of the meeting…”).
As to independent claim 6, Yoshioka et al. further teaches:
6. (Currently Amended) A signal processing program (see ¶ [0025 and 0028] citations as in claim 1, above and further ¶ [0024]: “…An operation can be performed using, software, hardware, firmware, or the like. The terms, “component,” “system,” and the like may refer to computer-related entities, hardware, and software in execution, firmware, or combination thereof. A component may be a process running on a processor, an object, an executable, a program, a function, a subroutine, a computer, or a combination of software and hardware. The term, “processor,” may refer to a hardware component, such as a processing unit of a computer system.”) for causing a computer to execute:
[the limitations as in claim 5, above.]
Regarding claim 13, 15, and 17, Yoshioka et al. teaches the limitations as in claims 1, 5, and 6, above.
Yoshioka et al. further teaches:
13, 15, and 17. (Currently Amended) The signal processing device/method/program according to claim 1, 5, and 6,
wherein speech recognition is performed to output a speech recognition result obtained by converting a message signal into text (see ¶ [0040]: “There may be additional devices that are within audio or visual range of the meeting 100, such as a digital assistant 148 or a dedicated meeting device 150, both of which are shown on the table 130, but can be anywhere within audio range of the meeting 100. Such additional devices may be connected to the distributed meeting server 135 and have their audio streams added to the meeting instance for processing to further enhance the audio and speech-to-text processing capabilities of the meeting instance running on the meeting server 135. Such additional devices may be detected by the meeting server 135 and added to the meeting as described above or may be presented to one or more of the users as an option to add to the meeting.”
¶ [0070]: “In various embodiments, the conversion of the audio signals to text that is used in conjunction with speaker identification and generation of the transcript that is diarized to identify speakers are provided by the meeting server 135.”
and ¶ [0101]: “The output from combination module 1060 is the result of a third fusion, referred to as a late fusion, to produce text and speaker identification for generation of a speaker-attributed transcript of the meeting…”).
Regarding claim 14, 16, and 18, Yoshioka et al. teaches the limitations as in claims 1, 5, and 6, above.
Yoshioka et al. further teaches:
14, 16, and 18. (Currently Amended) The signal processing device/method/program according to claim 1, 5, and 6,
wherein speech enhancement processing is performed using a trained deep learning model (see ¶ [0084 and 0098]: “[0084] In some embodiments, the beamforming module 1020 may be configured to separate overlapped speech signals of different users. This can make speech recognition and speaker attribution more accurate. In one embodiment, continuous speech separation for a distributed microphone recording system is performed via a neural network that is trained using permutation invariant training or its variant such as deep clustering or attractor network. To potentially save on computation, overlap detection may be used to determine whether or not the speech separation neural network should be executed for each period of time. If overlapped speech is not detected for a selected period of time, the neural network is not executed, saving processing resources and allowing the transcript to be produced more quickly in real time.
[0098] Multiple speaker diarization modules 1050, 1055 receive the outputs of the SR decoder modules 1040, 1045 as an N-best list for each segment. In one implementation, only the top word sequence hypothesis is used. A first operation extracts speaker embeddings, such as d-vectors (hidden layer activations of a deep neural network for speaker verification), at fixed intervals…”).
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 7, and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yoshioka et al. (US 20200349230 A1) and further in view of Chang et al. (US 20210314700 A1).
As to independent claim 1, Yoshioka et al. teaches:
1. (Currently Amended) A signal processing device (see ¶ [0025 and 0028]: “[0025] Furthermore, the claimed subject matter may be implemented as a method, apparatus, or article of manufacture using standard programming and engineering techniques to produce software, firmware, hardware, or any combination thereof to control a computing device to implement the disclosed subject matter… [0028] In response to a meeting having been detected or otherwise arranged, a meeting instance is generated on the meeting system to recognize speech from users that are speaking and to generate a transcript of the meeting…”) comprising:
at least one processor (see ¶ [0042]: “FIG. 2 is a block diagram of a user device 200 for use in meetings. Other devices that participate in the meeting may have a similar set of components. The device 200 includes at least one microphone 210 and a processor 215 for executing a meeting app 220 that is stored on memory 225…”); and
memory storing instructions that, when executed by the at least one processor, causes the device to perform a set of operations, the set of operations (see ¶ [0042] citation as in limitation above: “memory 225”) comprising:
generating, from an observation signal, an enhancement signal in which a voice of a speaker is enhanced (see ¶ [0025 and 0028] citations as in preamble above and further ¶ [0040]: “There may be additional devices that are within audio or visual range of the meeting 100, such as a digital assistant 148 or a dedicated meeting device 150, both of which are shown on the table 130, but can be anywhere within audio range of the meeting 100. Such additional devices may be connected to the distributed meeting server 135 and have their audio streams added to the meeting instance for processing to further enhance the audio and speech-to-text processing capabilities of the meeting instance running on the meeting server 135. Such additional devices may be detected by the meeting server 135 and added to the meeting as described above or may be presented to one or more of the users as an option to add to the meeting.”
¶ [0076-0077]: “[0076] Stream synchronization module 1015 provides a multi-channel synchronized signal, {[y.sub.0(t), . . . , y.sub.M-1(t)]; t=0, 1, . . . } to a beamforming module 1020. The beamforming module 1020 functions to separate overlapping speech. Overlapping speech occurs when two people in the meeting speak at the same time. Prior to recognizing the speech and converting the speech to text, the speech is first separated into separate channels. Thus with an M-channel input, the output is N-channels, and is referred to as an N-channel beamformed signal, {[z.sub.0(t), . . . , z.sub.N-1(t)]; t=0, 1, . . . }. The stream synchronization module 1015 acts as a first fusion point, where multiple outputs are generated to retain the diversity of the input information. Where no speech overlaps, such fusion is optional. [0077] FIG. 11 is a flowchart illustrating a computer-implemented method 1100 of synchronizing multiple audio channels received from multiple distributed devices during an intelligent meeting. At operation 1110, audio signals representative of streamed speech are received from multiple distributed devices to generate multiple audio channels. A selected one of the audio channels is designated at operation 1120 as a reference channel.”
and ¶ [0079-0081]: “[0079] Method 1100 may be performed periodically to correct the timing of the remaining audio channels, such as every 30 seconds. In one embodiment, method 1100 includes further operations to correct for the global offset caused at least by different clocks in the distributed devices. At operation 1150, a global offset is determined for each of the remaining audio channels. The remaining audio channels are then corrected at operation 1160 by each corresponding remaining audio channel global offset prior to correcting each remaining audio channel for the determined difference in time. [0080] Acoustic beamforming, or simply beamforming, is a technique to enhance target speech by reducing unwanted sounds such as background noise from multi-channel audio signals. Beamforming can improve accuracy of downstream speech processing, such as speech recognition and speaker diarization. [0081] For an intelligent meeting with audio streamed from multiple distributed devices whose exact positions relative to one another are not known, traditional beamforming algorithms, such as delay-and-sum beamforming, superdirective beamforming, and differential beamforming do not work. Such algorithms rely on prior knowledge about the arrangement of microphone devices, which is not available for distributed devices.”),
adding the observation signal to the enhancement signal (see ¶ [0025, 0028, 0040, 0076-0077, and 0079-0081] citations as in limitation(s) above. [0076-0077]: “overlapping speech” [0079-0081]: “delay-and-sum beamforming” and further Fig. 9 (910, 912, 914: devices/speech signals, 930: fusion and 940: transcript) and ¶ [0069-0070]: “[0069] The meeting transcriber 925 includes a synchronization module or function in addition to a speech recognition module or function. The audio signals from the audio channels 916, 918, and 920 are first synchronized and then recognized, resulting in texts associated with each of the channels according to one embodiment. The recognition outputs are then fused (by fusion 930) or otherwise processed to generate a transcript 940. The transcript 940 may then be provided back to the users. In other embodiments, the audio signals from the audio channels 916, 918, and 920 are fused before speech recognition. The audio signal obtained after the fusion is recognized, resulting in a single version of text. In some embodiments, the transcript may be provided with very little delay. [0070] In various embodiments, the conversion of the audio signals to text that is used in conjunction with speaker identification and generation of the transcript that is diarized to identify speakers are provided by the meeting server 135. The functions performed by the meeting server 135 include the synchronization, recognition, fusion, and diarization functions. While such functions are shown in a particular order in FIG. 9, in different embodiments, the functions may be performed in varying orders. For example, fusion may be performed prior to recognition and may also be performed at various other points as described below.”
as well as Fig. 10 (1020: beamforming module, fusion points, and 1060: Hypothesis combination) and ¶ [0101]: “The output from combination module 1060 is the result of a third fusion, referred to as a late fusion, to produce text and speaker identification for generation of a speaker-attributed transcript of the meeting…”); and
performing speech recognition on the enhancement signal to which the observation signal is added and processed using a trained deep learning model, in which the trained deep learning model converts the speech recognition result into text format (see Fig. 9-10 and ¶ [0025, 0028, 0040, 0076-0077, 0079-0081, and 0101] citations as in limitation(s) above. More specifically: [0076-0077]: “overlapping speech” [0079-0081]: “delay-and-sum beamforming”, Fig. 9 (910, 912, 914: devices/speech signals, 930: fusion and 940: transcript), Fig. 10 (1020: beamforming module, fusion points, and 1060: Hypothesis combination), ¶ [0070]: “In various embodiments, the conversion of the audio signals to text that is used in conjunction with speaker identification and generation of the transcript that is diarized to identify speakers are provided by the meeting server 135. […] For example, fusion may be performed prior to recognition and may also be performed at various other points as described below.” and ¶ [0101]: “The output from combination module 1060 is the result of a third fusion, referred to as a late fusion, to produce text and speaker identification for generation of a speaker-attributed transcript of the meeting…” and further ¶ [0084 and 0098]: “[0084] In some embodiments, the beamforming module 1020 may be configured to separate overlapped speech signals of different users. This can make speech recognition and speaker attribution more accurate. In one embodiment, continuous speech separation for a distributed microphone recording system is performed via a neural network that is trained using permutation invariant training or its variant such as deep clustering or attractor network … [0098] Multiple speaker diarization modules 1050, 1055 receive the outputs of the SR decoder modules 1040, 1045 as an N-best list for each segment. In one implementation, only the top word sequence hypothesis is used. A first operation extracts speaker embeddings, such as d-vectors (hidden layer activations of a deep neural network for speaker verification), at fixed intervals…”).
However, Yoshioka et al. does not explicitly teach, but Chang et al. does teach:
wherein the enhancement signal further comprises reduced artifact element, in which the artifact element is a vector perpendicular to the enhancement signal (see ¶ [0042]: “FIG. 7(c) depicts the second adaptation of the third embodiment of the invention involving three single-axis non-acoustic sensors, Non-acoustic Sensor 1, Non-acoustic Sensor 1b and Non-acoustic Sensor 1c. The intention of this adaptation is to suppress noise in the direction of the two axes perpendicular to the axis of the user's voice. For example, with respect to orientations defined in FIG. 7(a), the voice is along the x-axis while the noise is in the y- and z-axes. One single-axis non-acoustic sensor is used for each axis.”);
Yoshioka et al. and Chang et al. are considered to be analogous to the claimed invention because they are in the same field of endeavor in signal processing associated with plurality of signals. 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 Yoshioka et al. to incorporate the teachings of Chang et al. of wherein the enhancement signal further comprises reduced artifact element, in which the artifact element is a vector perpendicular to the enhancement signal which provides the benefit of improved signal-to-noise ratio obtained from a Non-acoustic Sensor over Acoustic Microphone ([0049] of Chang et al.).
Regarding claims 2, 7, and 10, Yoshioka et al. and Chang et al. teaches the limitations as in claims 1, 5, and 6, above.
Yoshioka et al. further teaches:
2, 7, and 10. (Original) The signal processing device/method/program according to claims 1, 5, and 6,
wherein the observation signal is an audio signal recorded by a single microphone (see ¶ [0034]: “FIG. 1 is a perspective view of a meeting 100 between multiple users. A first user 110 has a first device 115 that includes a microphone to capture audio, including speech…” and ¶ [0068]: “…The users each may have an associated (distributed) device 910, 912, 914 that are equipped with microphones to capture audio, including speech by the various users at the meeting and provide the captured audio as audio signals to a meeting server, which includes at least a meeting transcriber 925, via audio channels 916, 918, and 920, respectively. ”).
Claims 3-4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yoshioka et al. (US 20200349230 A1) and further in view of Chang et al. (US 20210314700 A1) as applied to claim 1, above, and further in view of Shoichiro (JP 2021047040 A).
Regarding claim 3, Yoshioka et al. and Chang et al. teaches the limitations as in claim 1, above.
However, Yoshioka et al. and Chang et al. does not explicitly teach, but Shoichiro does teach:
3. (Currently Amended) The signal processing device according to claim 1
wherein a weight of an observation signal to be added is adjusted to the enhancement signal according to a ratio of a noise signal included in the observation signal (see ¶ 6 of page 3: “FIG. 4 is a diagram showing a configuration example of the signal processing unit 5 in the present embodiment. The signal processing unit 5 includes a communication I / F (interface) 51, a beam signal forming unit 52, a pulse compression unit 53, a noise threshold processing unit 54, a CFAR (Constant False Alarm Ratio) processing unit 55, and SLB processing…”
¶ 2 of page 7: “The noise threshold processing unit 54 removes noise and the like in the phased array antenna 1 included in the Σ beam signal supplied from the pulse compression unit 53. Noise removal is performed by setting a threshold value based on the amplitude of the noise signal measured for each reception and removing signals below the threshold value. The noise threshold processing unit 54 supplies the noise-removed Σ beam signal to the CFAR [i.e., constant false alarm ratio] processing unit 55.”).
Yoshioka et al. and Chang et al. and Shoichiro are considered to be analogous to the claimed invention because they are in the same field of endeavor in signal processing associated with plurality of signals. 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 Yoshioka et al. and Chang et al. to incorporate the teachings of Shoichiro of wherein the addition unit adjusts a weight of an observation signal to be added to the enhancement signal according to a ratio of a noise signal included in the observation signal which provides the benefit of Providing a system capable of suppressing the influence of unnecessary signals (abstract of Shoichiro).
Regarding claim 4, Yoshioka et al. and Chang et al. in combination with Shoichiro teach the limitations as in claim 3, above.
Shoichiro further teaches:
4. (Original) The signal processing device according to claim 3,
wherein only an observation signal to be added to the enhancement signal is weighted, or both the observation signal and the observation signal to be added to the enhancement signal are weighted in a relationship in which a sum of a weight of the observation signal and a weight of the observation signal to be added to the enhancement signal is 1 (see ¶ 3 of page 4: “Further, the beam signal forming unit 52 multiplies the digital IQ signals of the sub-array antennas 11 included in each of the sub-arrays A to D by a weight (weighting coefficient), adds and synthesizes them, and calculates the weighted composite signals of the sub-arrays A to D. At least three weights are predetermined, one of which is a uniform weight for the digital IQ signal of each subarray antenna 11. The uniform weight is, for example, "1". As other weights, for example, a weight corresponding to the directivity of the Taylor distribution or a weight corresponding to the directivity of the Bayliss distribution or the Chebyshev distribution may be used. Further, in the main lobe of the phased array antenna 1, another weighting coefficient in which the amplitude (gain) of the signal obtained by weighting addition is smaller than the amplitude (gain) of the Σ beam signal may be used.”
¶ 2 of page 6: “FIG. 8 is a diagram showing an example of a Σ beam signal (sum signal) calculated by the beam signal forming unit 52 in the present embodiment and two ΔEL beam signals for SLB. In the example shown in FIG. 8, two weights are used as the weights used when calculating the ΔEL beam signal for SLB. The first weight is a weight corresponding to the directivity of the Taylor distribution. The second weight is a weight that selects two predetermined sub-array antennas 11 from the sub-array antennas 11 included in the sub-arrays A to D, and adds and synthesizes the digital IQ signals of the selected sub-array antennas 11. For example, any two values of the elements of the weight W = [w1, w2, w3, w4, w5] are set to "1", and the other values are set to "0". The null points of the two SLB ΔEL beam signals calculated in this way appear at different angles in the sidelobe range. By comparing the amplitudes of these two SLB ΔEL beam signals with the amplitudes of the Σ beam signals, it is possible to correctly determine the sidelobe range.”).
Yoshioka et al. and Chang et al. and Shoichiro are considered to be analogous to the claimed invention because they are in the same field of endeavor in signal processing associated with plurality of signals. 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 Yoshioka et al. and Chang et al. to incorporate the teachings of Shoichiro of wherein the addition unit weights only an observation signal to be added to the enhancement signal, or weights both the observation signal and the observation signal to be added to the enhancement signal in a relationship in which a sum of a weight of the observation signal and a weight of the observation signal to be added to the enhancement signal is 1 which provides the benefit of Providing a system capable of suppressing the influence of unnecessary signals (abstract of Shoichiro).
Claims 8-9, and 11-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yoshioka et al. (US 20200349230 A1) as applied to claims 5 and 6 above, and further in view of Shoichiro (JP 2021047040 A).
Regarding claim 8, and 11, Yoshioka et al. teaches the limitations as in claims 5, and 6, above.
However, Yoshioka et al. does not explicitly teach, but Shoichiro does teach:
8, and 11. (Previously Presented) The signal processing device/method/program according to claims 5, and 6,
wherein the addition unit adjusts a weight of an observation signal to be added to the enhancement signal according to a ratio of a noise signal included in the observation signal (see ¶ 6 of page 3 and ¶ 2 of page 7 citations as in claim 3, above.).
Yoshioka et al. and Shoichiro are considered to be analogous to the claimed invention because they are in the same field of endeavor in signal processing associated with plurality of signals. 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 Yoshioka et al. to incorporate the teachings of Shoichiro of wherein the addition unit adjusts a weight of an observation signal to be added to the enhancement signal according to a ratio of a noise signal included in the observation signal which provides the benefit of Providing a system capable of suppressing the influence of unnecessary signals (abstract of Shoichiro).
Regarding claims 9 and 12, Yoshioka et al. teaches the limitations as in claims 5, and 6, above.
However, Yoshioka et al. does not explicitly teach, but Shoichiro does teach:
9, and 12. (Previously Presented) The signal processing device/method/program according to claims 5, and 6,
wherein the addition unit weights only an observation signal to be added to the enhancement signal, or weights both the observation signal and the observation signal to be added to the enhancement signal in a relationship in which a sum of a weight of the observation signal and a weight of the observation signal to be added to the enhancement signal is 1 (see ¶ 3 of page 4 and ¶ 2 of page 6 citations as in claim 4, above.).
Yoshioka et al. and Shoichiro are considered to be analogous to the claimed invention because they are in the same field of endeavor in signal processing associated with plurality of signals. 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 Yoshioka et al. to incorporate the teachings of Shoichiro of wherein the addition unit weights only an observation signal to be added to the enhancement signal, or weights both the observation signal and the observation signal to be added to the enhancement signal in a relationship in which a sum of a weight of the observation signal and a weight of the observation signal to be added to the enhancement signal is 1 which provides the benefit of Providing a system capable of suppressing the influence of unnecessary signals (abstract of Shoichiro).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
JP 2000082999 A: Determines an optimal signal adding rate for input signals based on SNR and performs weighting on noise reduced signals.
[0008] First, in step 31, calculates the .sub.SNR k (n) '= P X, k (n) / P N, k (n) SNR k defined in (11) (n)'. Next, in step 32, for the determined SNR .sub.k (n) ′, (1 SNR .sub.k by averaging using the estimated value (noise reduced power) P .sub.Y, k (n-1) one time ago represented by the expression (3) (n). That is, SNR .sub.k (n) = (1−β) P [SNR .sub.k (n) ′ − 1] + β [P .sub.Y, k (n−1) / P .sub.N, k (n−1)] (12) . P [*] takes * if * is positive and 0 if * is negative. This SNR .sub.k (n) and, if necessary, SNR .sub.k (n) ′ Is transferred to the gain factor calculator 27. In the gain factor calculation unit 27, the instantaneous S SNR .sub.k (n) transferred from the / N ratio estimation unit 201, In some cases, using this and SNR .sub.k (n) ′, a gain factor G (SNR .sub.k (n)) at each frequency defined in each noise reduction scheme is calculated. The gain factor G (SNR .sub.k (n)) is transferred to the gain factor insertion unit 28. FIG. 7 shows a gain factor according to each method. SNR .sub.k is i.e. three methods above in FIG. 5 (n) is used to determine the gain factor, but when the lowest MMSE method is used, SNR .sub.k (n) and SNR .sub.k (n) 'is used. The gain factor insertion unit 28 performs noise reduction for each band using the gain factor calculated by the gain factor calculation unit 27. That is, the band signal P transferred from the input signal power calculator 24 .sub.With respect to .sub.X, k (n), a band output P .sub.Y, obtained by calculating P .sub.Y, k (n) = G (SNR .sub.k (n)) × P .sub.X, k (n) (13) to reduce noise Output .sub.k (n). P .sub.Y, k (n) is transferred to the time domain transformation unit 29, and Y .sub.k (n) = Y .sub.k, r (n) using Φ .sub.k (n) sent from the input signal phase calculation unit 25. + JY .sub.k, i (n) where Y .sub.k, r (n) = √P .sub.Y, k (n) cos [Φ .sub.k (n)] Y .sub.k, i (n) = √P .sub.Y, k (n) sin [Φ .sub.k (n)] (14), synthesized into a full-band signal, and further converted into a time-domain signal by, for example, an inverse discrete Fourier transform. The D / A converter 30 converts the result into an analog signal, and outputs a signal 17, Y (n) in which noise is reduced.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Keisha Y Castillo-Torres whose telephone number is (571)272-3975. The examiner can normally be reached Monday - Friday, 9:00 am - 4:00 pm (EST).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pierre-Louis Desir can be reached at (571)272-7799. 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.
Keisha Y. Castillo-Torres
Examiner
Art Unit 2659
/Keisha Y. Castillo-Torres/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
Prosecution Insights