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 .
DETAILED ACTION
Response to Arguments
Applicant's arguments with respect to claims 1, 2, and 21-38 have been considered but are moot in view of the new ground(s) of rejection. Applicant’s arguments are directed to the amended subject matter; new citations from existing prior art as well as new prior art is provided below.
Note: The claims are not directed towards patent ineligible subject matter under 35 U.S.C. 101
Step 1: IS THE CLAIM DIRECTED TO A PROCESS, MACHINE, MANUFACTURE OR COMPOSITION OF MATTER?
Yes
Step 2A.1: IS THE CLAIM DIRECTED TO A LAW OF NATURE, A NATURAL PHENOMENON (PRODUCT OF NATURE) OR AN ABSTRACT IDEA?
No
Step 2A.2: DOES THE CLAIM RECITE ADDITIONAL ELEMENTS THAT INTEGRATE THE JUDICIAL EXCEPTION INTO A PRACTICAL APPLICATION?
Yes, if the claims are alternatively construed to be abstract in step 2A1. The claims seek to improve ASR accuracy using intelligibility scoring using neural layers supported by the specification, and reflected by the claims e.g. in spec: 0037 0040 0041. In other words, the claims enable the invention to fine tune accuracy of patterns of intelligibility while reducing processing complication, inefficiency, and bandwidth issues.
Supported by the following:
In Finjan Inc. v. Blue Coat Systems, Inc., 879 F.3d 1299, 125 USPQ2d 1282 (Fed. Cir. 2018), the claimed invention was a method of virus scanning that scans an application program, generates a security profile identifying any potentially suspicious code in the program, and links the security profile to the application program. 879 F.3d at 1303-04, 125 USPQ2d at 1285-86. The Federal Circuit noted that the recited virus screening was an abstract idea, and that merely performing virus screening on a computer does not render the claim eligible. 879 F.3d at 1304, 125 USPQ2d at 1286. The court then continued with its analysis under part one of the Alice/Mayo test by reviewing the patent’s specification, which described the claimed security profile as identifying both hostile and potentially hostile operations. The court noted that the security profile thus enables the invention to protect the user against both previously unknown viruses and “obfuscated code,” as compared to traditional virus scanning, which only recognized the presence of previously-identified viruses. The security profile also enables more flexible virus filtering and greater user customization. 879 F.3d at 1304, 125 USPQ2d at 1286. The court identified these benefits as improving computer functionality, and verified that the claims recite additional elements (e.g., specific steps of using the security profile in a particular way) that reflect this improvement. Accordingly, the court held the claims eligible as not being directed to the recited abstract idea. 879 F.3d at 1304-05, 125 USPQ2d at 1286-87. This analysis is equivalent to the Office’s analysis of determining that the additional elements integrate the judicial exception into a practical application at Step 2A Prong Two, and thus that the claims were not directed to the judicial exception (Step 2A: NO).
Examples of claims that improve technology and are not directed to a judicial exception include: Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1339, 118 USPQ2d 1684, 1691-92 (Fed. Cir. 2016) (claims to a self-referential table for a computer database were directed to an improvement in computer capabilities and not directed to an abstract idea); McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1315, 120 USPQ2d 1091, 1102-03 (Fed. Cir. 2016) (claims to automatic lip synchronization and facial expression animation were directed to an improvement in computer-related technology and not directed to an abstract idea); Visual Memory LLC v. NVIDIA Corp., 867 F.3d 1253,1259-60, 123 USPQ2d 1712, 1717 (Fed. Cir. 2017) (claims to an enhanced computer memory system were directed to an improvement in computer capabilities and not an abstract idea); Finjan Inc. v. Blue Coat Systems, Inc., 879 F.3d 1299, 125 USPQ2d 1282 (Fed. Cir. 2018) (claims to virus scanning were found to be an improvement in computer technology and not directed to an abstract idea); SRI Int’l, Inc. v. Cisco Systems, Inc., 930 F.3d 1295, 1303 (Fed. Cir. 2019) (claims to detecting suspicious activity by using network monitors and analyzing network packets were found to be an improvement in computer network technology and not directed to an abstract idea). Additional examples are provided in MPEP § 2106.05(a).
Regarding the December 5th 2025 Memo in light of September 26, 2025 Appeals Review Panel Decision in Ex parte Desjardins, Appeal 2024-000567 for Application 16/319,040, in deciding if a recited abstract idea does or does not direct the entire claim to an abstract idea, when a claim is considered as a whole:
Paragraph 21 of the Specification, which the Appellant cites, identifies improvements in training the machine learning model itself. Of course, such an assertion in the Specification alone is insufficient to support a patent eligibility determination, absent a subsequent determination that the claim itself reflects the disclosed improvement. See MPEP § 2106.05(a) (citing Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1316 (Fed. Cir. 2016)). Here, however, we are persuaded that the claims reflect such an improvement. For example, one improvement identified in the 8 Appeal2024-000567 Application 16/319,040 Specification is to "effectively learn new tasks in succession whilst protecting knowledge about previous tasks." Spec. ,r 21. The Specification also recites that the claimed improvement allows artificial intelligence (AI) systems to "us[e] less of their storage capacity" and enables "reduced system complexity." Id. When evaluating the claim as a whole, we discern at least the following limitation of independent claim 1 that reflects the improvement: "adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task." We are persuaded that constitutes an improvement to how the machine learning model itself operates, and not, for example, the identified mathematical calculation. Under a charitable view, the overbroad reasoning of the original panel below is perhaps understandable given the confusing nature of existing § 101 jurisprudence, but troubling, because this case highlights what is at stake. Categorically excluding AI innovations from patent protection in the United States jeopardizes America's leadership in this critical emerging technology. Yet, under the panel's reasoning, many AI innovations are potentially unpatentable-even if they are adequately described and nonobvious-because the panel essentially equated any machine learning with an unpatentable "algorithm" and the remaining additional elements as "generic computer components," without adequate explanation. Dec. 24. Examiners and panels should not evaluate claims at such a high level of generality.
Specifically, Ex Parte Desjardins explained the following:
Enfish ranks among the Federal Circuit's leading cases on the eligibility of technological improvements. In particular, Enfish recognized that “[m]uch of the advancement made in computer technology consists of improvements to software that, by their very nature, may not be defined by particular physical features but rather by logical structures and processes.” 822 F.3d at 1339. Moreover, because “[s]oftware can make non-abstract improvements to computer technology, just as hardware improvements can,” the Federal Circuit held that the eligibility determinations should turn on whether “the claims are directed to an improvement to computer functionality versus being directed to an abstract idea.” Id. at 1336. (Desjardins, page 8).
Further in Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential), the claimed invention was a method of training a machine learning model on a series of tasks. The Appeals Review Panel (ARP) overall credited benefits including reduced storage, reduced system complexity and streamlining, and preservation of performance attributes associated with earlier tasks during subsequent computational tasks as technological improvements that were disclosed in the patent application specification. Specifically, the ARP upheld the Step 2A Prong One finding that the claims recited an abstract idea (i.e., mathematical concept). In Step 2A Prong Two, the ARP then determined that the specification identified improvements as to how the machine learning model itself operates, including training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting” encountered in continual learning systems. Importantly, the ARP evaluated the claims as a whole in discerning at least the limitation “adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task” reflected the improvement disclosed in the specification. Accordingly, the claims as a whole integrated what would otherwise be a judicial exception instead into a practical application at Step 2A Prong Two, and therefore the claims were
The claim itself does not need to explicitly recite the improvement described in the specification (e.g., “thereby increasing the bandwidth of the channel”). See, e.g., Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential), in which the specification identified the improvement to machine learning technology by explaining how the machine learning model is trained to learn new tasks while protecting knowledge about previous tasks to overcome the problem of “catastrophic forgetting,” and that the claims reflected the improvement identified in the specification. Indeed, enumerated improvements identified in the Desjardins specification included disclosures of the effective learning of new tasks in succession in connection with specifically protecting knowledge concerning previously accomplished tasks; allowing the system to reduce use of storage capacity; and the enablement of reduced complexity in the system. Such improvements were tantamount to how the machine learning model itself would function in operation and therefore not subsumed in the identified mathematical calculation.
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 –
(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.
Claims 1, 2, 21, 27-29, 31-35, 37, and 38 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US 20240153520 A1 Solomon; Merrill et al. (hereinafter Solomon).
Re claim 1, Solomon teaches
1. A computer-implemented method, executed on a computing device, comprising: (fig. 1)
receiving a degraded audio signal (a noisy or distorted signal input into an ASR 0022 0027)
generating, by a pretrained automatic speech recognition (ASR) system, a transcript of the degraded audio signal and ASR encoder features of the degraded audio signal, wherein the ASR encoder features include intermediate representations or encoder activations extracted from the degraded audio signal prior to generation of the transcript; (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
processing the ASR encoder features to recognize patterns, within the ASR encoder features, degraded audio signal (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
determining a predicted intelligibility of the degraded audio signal based on the patterns [[of]] within the ASR encoder features. (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claim 33, this claim has been rejected for teaching a broader, or narrower claim based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
For instance, see fig. 1 and fig. 7 of Solomon.
Re claim 37, this claim has been rejected for teaching a broader, or narrower claim based on general inclusion of hardware alone (e.g. processor, memory, instructions), representation of claim 1 omitting/including hardware for instance, otherwise amounting to a virtually identical scope
For instance, see fig. 1 and fig. 7 of Solomon.
Re claims 2, 34, and 38, Solomon teaches
2. The computer-implemented method of claim 1 further including generating an intelligibility score based on the predicted intelligibility. (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claims 21 and 35, Solomon teaches
21. (New) The computer-implemented method of claim 2, wherein the intelligibility score indicates a level of understandability of speech in the degraded audio signal. (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern withquality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claim 27, Solomon teaches
27. (New) The computer-implemented method of claim 1, wherein determining the predicted intelligibility comprises using background acoustic features of the degraded audio signal in combination with the ASR encoder features. (background noise/data can be spectral data per se and also in 0055 and later processed 0028 and fig. 2, in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claim 28, Solomon teaches
28. (New) The computer-implemented method of claim 1, wherein determining the predicted intelligibility comprises using spectral features of the degraded audio signal in combination with the ASR encoder features. (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claim 29, Solomon teaches
29. (New) The computer-implemented method of claim 1, wherein processing the ASR encoder features comprises processing the ASR encoder features using an intelligibility estimator trained to predict acoustic speech intelligibility based on ASR encoder features. (in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claim 31, Solomon teaches
31. (New) The computer-implemented method of claim 1, further comprising controlling operation of the pretrained ASR system based on the predicted intelligibility. (learning and training thereof, as in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Re claim 32, Solomon teaches
32. (New) The computer-implemented method of claim 31, wherein controlling operation of the pretrained ASR system comprises suppressing or discarding the transcript when the predicted intelligibility satisfies a low-intelligibility condition. (choosing the best file, initially in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 22-26 and 36 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20240153520 A1 Solomon; Merrill et al. (hereinafter Solomon) in view of US 20230215429 A1 LEMBERSKY; Gennadi et al. (hereinafter LEMBERSKY).
Re claims 22 and 36, Solomon teaches
22. (New) The computer-implemented method of claim 1, wherein the ASR encoder features are generated from one or more processing layers of an ASR encoder of the pretrained ASR system. (DNN and neural networks inherently contain layers per se, and in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
However, while Solomon teaches ASR intelligibility scoring in a DNN as part of a codec encoder/decoder, inherently containing layers in a neural network structure with iterative learning (i.e. a layer for each process spectral data may have a layer while phonetic may also have one), it does not expressly teach “layers” per se:
Layers (LEMBERSKY recognizing patterns in an ASR system utilizing VAD to determine human segments for instance with multiple layers to process distinct attributes 0018 and 0048-0050)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Solomon to incorporate the above claim limitations as taught by LEMBERSKY to allow for simple substitution of one known element for another to obtain predictable results such as the distinct attribute layers of LEMBERSKY into the existing inherent layers of Solomon’s DNN, which improves intelligibility by enabling hierarchical feature extraction i.e. lower layers capture spectral details, while higher layers model complex, long-term contextual dependencies, wherein when combined with VAD, this approach reduces WER (for instance) in noisy, reverberant environments while taking into account the noise for reconstruction of human intelligible portions.
Re claim 23, while Solomon teaches ASR intelligibility scoring in a DNN as part of a codec encoder/decoder, inherently containing layers and scores in a neural network structure with iterative learning (i.e. a layer for each process spectral data may have a layer while phonetic may also have one), it does not expressly teach “layers” per se with weights claimed:
23. (New) The computer-implemented method of claim 22, wherein the ASR encoder features comprise a weighted combination of features generated from multiple processing layers of the ASR encoder. (LEMBERSKY layers with weights in ASR in feature extraction 0043-0050 where layers are trained and scored per se 0018, recognizing patterns in an ASR system utilizing VAD to determine human segments for instance with multiple layers to process distinct attributes 0018 and 0048-0050)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Solomon to incorporate the above claim limitations as taught by LEMBERSKY to allow for simple substitution of one known element for another to obtain predictable results such as the distinct attribute layers of LEMBERSKY into the existing inherent layers of Solomon’s DNN, using weighted layers in ASR and machine learning, which improves intelligibility by enabling hierarchical feature extraction i.e. lower layers capture spectral details, while higher layers model complex, long-term contextual dependencies, wherein when combined with VAD, this approach reduces WER (for instance) in noisy, reverberant environments while taking into account the noise for reconstruction of human intelligible portions.
Re claim 24, While Solomon teaches ASR intelligibility scoring in a DNN as part of a codec encoder/decoder, inherently containing layers in a neural network structure with iterative learning (i.e. a layer for each process spectral data may have a layer while phonetic may also have one), it does not expressly teach “layers” per se:
24. (New) The computer-implemented method of claim 22, wherein the one or more processing layers are selected based on evaluating output quality associated with respective processing layers of the ASR encoder. (LEMBERSKY recognizing patterns in an ASR system utilizing VAD to determine human segments for instance with multiple layers to process distinct attributes 0018 and 0048-0050)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Solomon to incorporate the above claim limitations as taught by LEMBERSKY to allow for simple substitution of one known element for another to obtain predictable results such as the distinct attribute layers of LEMBERSKY into the existing inherent layers of Solomon’s DNN, using weighted layers in ASR and machine learning, which improves intelligibility by enabling hierarchical feature extraction i.e. lower layers capture spectral details, while higher layers model complex, long-term contextual dependencies, wherein when combined with VAD, this approach reduces WER (for instance) in noisy, reverberant environments while taking into account the noise for reconstruction of human intelligible portions.
Re claim 25, While Solomon teaches ASR intelligibility scoring in a DNN as part of a codec encoder/decoder, inherently containing layers in a neural network structure with iterative learning (i.e. a layer for each process spectral data may have a layer while phonetic may also have one), it does not expressly teach “layers” per se or VAD concepts thereof:
25. (New) The computer-implemented method of claim 1, further comprising using voice activity detection (VAD) to identify speech-containing portions of the degraded audio signal. (LEMBERSKY recognizing patterns in an ASR system utilizing VAD to determine human segments for instance with multiple layers to process distinct attributes 0018 and 0048-0050, and recognizing patterns in an ASR system utilizing VAD to determine human segments for instance with multiple layers to process distinct attributes 0018 and 0048-0050)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Solomon to incorporate the above claim limitations as taught by LEMBERSKY to allow for simple substitution of one known element for another to obtain predictable results such as the distinct attribute layers of LEMBERSKY into the existing inherent layers of Solomon’s DNN, which improves intelligibility by enabling hierarchical feature extraction i.e. lower layers capture spectral details, while higher layers model complex, long-term contextual dependencies, wherein when combined with VAD, this approach reduces WER (for instance) in noisy, reverberant environments while taking into account the noise for reconstruction of human intelligible portions.
Re claim 26, Solomon teaches
26. (New) The computer-implemented method of claim 25, wherein determining the predicted intelligibility comprises determining the predicted intelligibility based on portions of the ASR encoder features corresponding to the speech-containing portions of the degraded audio signal. (DNN and neural networks inherently contain layers per se, and in fig. 1 audio spectral analysis is performed as an intermediate representation or encore activation i.e. spectral data, this data is passed to the codec encoder prior to ASR, note there is a second ASR process at step 009 therefore the spectral data is extracted prior to the ASR output i.e. transcription or put another way spectral data (intermediate) is derived for the distorted signal prior to ASR output 009, then according to fig. 1 with 0022, indelibility scoring is used by using the best output transcript or ASR output based on the score e.g. level as in a score POLQA intelligibility score, discovering intelligibility pattern with quality metrics for instance, spectrum analysis (fig. 1), and also background noise/data (0028 and fig. 2), … using a CODEC with encoder, extracted parameters/features from a noisy or distorted signal input into an ASR 0022 0027)
Claim 30 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20240153520 A1 Solomon; Merrill et al. (hereinafter Solomon) in view of US 20240087596 A1 NANDWANA; Mahesh Kumar et al. (hereinafter NANDWANA).
Re claim 30, While Solomon teaches ASR intelligibility scoring in a DNN as part of a codec encoder/decoder, for learning, it does not teach labeled or human labeled ground truth:
30. (New) The computer-implemented method of claim 29, wherein the intelligibility estimator is trained using ground truth labels generated from an intrusive intelligibility algorithm or human listening tests. (NANDWANA 0073 ground truth via human labeling by listening for learning for input audio streams)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Solomon to incorporate the above claim limitations as taught by NANDWANA to allow for combining prior art elements according to known methods to yield predictable results such as using well known ground-truth as input data to a learning model, where the data in the learning model can use labeled instances by humans to directly capture how actual humans perceive and understand speech under various conditions, and when AI or autonomous learning metrics fail or become unreliable when dealing with non-linear distortions, severe background noise, reverberation, or aggressive audio compression, a ground-truth can improve false optimization to produce actual imperfect but audible cleaned up speech.
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 extension fee 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 date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20180233127 A1 VISSER; ERIK et al.
Intelligibility analysis of speech
US 20240389934 A1 Norel; Raquel et al.
Intelligibility scores for speech
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL COLUCCI whose telephone number is (571)270-1847. The examiner can normally be reached on M-F 9 AM - 7 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Flanders can be reached at (571)272-7516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MICHAEL COLUCCI/Primary Examiner, Art Unit 2655 (571)-270-1847
Examiner FAX: (571)-270-2847
Michael.Colucci@uspto.gov
