DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Change in Examiner
The Examiner of record has changed from Cameron Young to Paras Shah.
Response to Amendments and Arguments
The Applicant has amended the independent claims to recite the limitations of “wherein performing feature fusion of the living millimeterwave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: tracking and learning effective features of a target by frame streams via a correlation filter, modeling a region of interest, and generating the fusion response diagram of the living voice signal, wherein the target comprises a spectral energy trajectory of the living audio signal or the living millimeter wave signal.” Therefore, the Applicant’s arguments are moot based on these amendments and a new grounds for rejection have been applied in light of these amendments. Please see the update mappings found below.
The Applicant should provide more details as to what the “response diagram” is as it has been given a broad interpretation and how it is created. The Examiner recommends reviewing Fig 4 and para 0070-0071 of the as filed Specification.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
In this case, the limitations of the claims interpreted under 35 U.S.C. § 112(f) are those found within claim 8. Namely, the limitations reciting “means for…” These limitations are understood to mean the broadest reasonable interpretation of the corresponding specification, particularly ¶¶ [0053] – [0109].
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 5-6, 8-10, 13-14, 16-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication 2023/0090763 A1 to Muhammed Zahid Ozturk et al. (hereinafter Ozturk) in view of Lin (CN 113744731A)
Regarding claim 1, Ozturk teaches an identity recognition method, comprising:
obtaining a signal to be identified which comprises a millimeter wave signal and an audio signal; (Ozturk teaches receiving both audio signals and mmWave signals (i.e., a signal is obtained comprising both a mmWave signal and an audio signal.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring a living millimeter wave signal and a living audio signal; (Ozturk teaches performing voice detection, including extracting vocal fold vibration (i.e., living audio signal) and heartrate monitoring (i.e., living mmWave signal). Ozturk at ¶¶ [0256] - [0262], [0276] - [0298] and Fig. 9.)
performing feature fusion of the living millimeter wave signal and the living audio signal, and acquiring a fusion response diagram of a living voice signal; (Ozturk teaches receiving both audio signals and mmWave signals (i.e., a signal is obtained comprising both a mmWave signal and an audio signal.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299]. Further, Ozturk teaches reshaping the input data and representing the input data as a 3D representation during the fusion of the mmWave data and the audio data (i.e., a fusion response diagram.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
Ozturk, however, does not alone teach performing identity recognition based on the fusion response diagram of the living voice signal, wherein performing feature fusion of the living millimeterwave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: tracking and learning effective features of a target by frame streams via a correlation filter, modeling a region of interest, and generating the fusion response diagram of the living voice signal, wherein the target comprises a spectral energy trajectory of the living audio signal or the living millimeter wave signal.
In a similar field of endeavor, (e.g., the verification of users via mmWave voice detection), Lin teaches performing identity recognition based on the fusion response diagram of the living voice signal (see [0028], where determining whether the target audio signal and target mmWave signal original from the target user determined from LPC component as well as based on spectral entropy being greater than a threshold to determine human voice and the multiplication of the mmWave with the audio signal), wherein performing feature fusion of the living millimeterwave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: tracking and learning effective features of a target by frame streams via a correlation filter (see [0072], where VAD is determined based on correlation between mmWave and audio signals), modeling a region of interest, and generating the fusion response diagram of the living voice signal, wherein the target comprises a spectral energy trajectory of the living audio signal or the living millimeter wave signal (see [0018], [0022]-[0026], where determination of human information is determined based on spectral entropy is greater than a threshold (e.g. The examiner interprets the “spectral entropy” to be a function of spectral energy and therefore is the claimed “spectral energy trajectory” since this information is used to determine if human speech is present and once determined [0028] notes the determination using LPC whether the audio is from a target user) (e.g. The Examiner interprets the fusion response diagram to be the multiplication of the mmWave with the audio signal as noted in para [0022]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date to combine the teachings of Ozturk with the teachings of Lin to provide performing identity recognition based on the fusion response diagram. Doing so would have provided a method to detect signals originating from a human when many people are present (see Lin [0155]).
Regarding claim 2, Ozturk in view of Lin (hereinafter Lin) teaches all the limitations of claim 1, further Ozturk teaches the identity recognition method of claim 1, wherein before the performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring the living millimeter wave signal and the living audio signal, the method further comprises: performing voice activity detection of the millimeter wave signal and the audio signal, and acquiring a millimeter wave signal and an audio signal with voice activity; (Ozturk teaches performing voice detection and speech recognition using mmWave technology to activate audio recognition (i.e., the mmWave signal and audio signal are retrieved with voice activity detection.) Ozturk at ¶¶ [0436] and [0276] - [0299].) and
performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring a denoised millimeter wave signal and a denoised audio signal. (Ozturk contemplates using denoising as a step within preprocessing (see Ozturk at ¶ [0180]). Further, Ozturk discusses preprocessing both the mmWave signal and the audio signal received as demonstrated at Fig. 9. Ozturk at Fig. 9 and ¶¶ [0276] - [0299].1)
Regarding claim 5, Ozturk-Lin teaches all the limitations of claim 1 as laid out above. Further, Ozturk teaches the identity recognition method of claim 1, wherein the performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring the living millimeter wave signal and the living audio signal further comprises: extracting living feature of millimeter wave and living feature of audio based on the millimeter wave signal and the audio signal, respectively; (Ozturk teaches extracting features of audio signals and radio wave (i.e., mmWave) signals. Ozturk at ¶¶ [0265] - [0273].)
calculating similarity coefficients based on the living feature of millimeter wave and the living feature of audio, and generating a dual-mode reference signal based on the similarity coefficients; and (Ozturk contemplates calculating similarity scores between two vectors of the channel information (i.e., the signal information). Ozturk at ¶¶ [0205] - [0208]. Further, Ozturk teaches processing both mmWave signals and Audio signals to fuse them for masking and speech detection. Ozturk at ¶¶ [0276] - [0299] and Fig. 9. Therefore, the similarity scores calculated for the vectors are used in fusing the mmWave signals and the audio signals. As such, a dual-mode reference signal is output by the fusion operation.)
inputting the dual-mode reference signal into a classification model, and acquiring the living millimeter wave signal and the living audio signal, wherein the classification model is trained by using a standard data set. (Ozturk teaches performing a classification task based on time series data as input (i.e., the channel information takes the form of or includes time-series information as laid out by Ozturk at ¶¶ [0047] - [0050] and [0396] - [0398].). Therefore, Ozturk teaches performing classification on the "dual-mode reference signal" as part of VAD wherein the classification is trained on a standard dataset (Ozturk also teaches training classifiers at ¶¶ [0154] - [0155]. Further still Ozturk teaches training the classifier based on a training time series channel information (TSCI) (i.e., a standard dataset). Ozturk at ¶¶ [0154] - [0155].))
Regarding claim 6, Ozturk-Lin teaches all the limitations of claim 1 as laid out above. Further, Ozturk teaches the identity recognition method of claim 1, wherein the performing feature fusion of the living millimeter wave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: generating a millimeter wave response diagram and an audio response diagram based on the living millimeter wave signal and the living audio signal, respectively; and fusing the millimeter wave response diagram and the audio response diagram, and acquiring the fusion response diagram of the living voice signal. (Ozturk teaches receiving both audio signals and mmWave signals (i.e., a signal is obtained comprising both a mmWave signal and an audio signal.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299]. Further, Ozturk teaches reshaping the input data and representing the input data as a 3D representation during the fusion of the mmWave data and the audio data (i.e., a fusion response diagram.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299]. That is, Ozturk’s fusion and representation of the signals in a 3D representation amount to generating a response diagram and fusing the diagrams of the signals into a single diagram.)
Regarding claim 8, as best understood in light of the interpretation under 35 U.S.C. 112(f) laid out above, Ozturk teaches an identity recognition apparatus, comprising: means for obtaining a signal to be identified which comprises a millimeter wave signal and an audio signal; (Ozturk teaches receiving both audio signals and mmWave signals (i.e., a signal is obtained comprising both a mmWave signal and an audio signal.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
means for performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring a living millimeter wave signal and a living audio signal; (Ozturk teaches performing voice detection, including extracting vocal fold vibration (i.e., living audio signal) and heartrate monitoring (i.e., living mmWave signal). Ozturk at ¶¶ [0256] - [0262], [0276] - [0298] and Fig. 9.)
means for performing feature fusion of the living millimeter wave signal and the living audio signal, and acquiring a fusion response diagram of a living voice signal; (Ozturk teaches receiving both audio signals and mmWave signals (i.e., a signal is obtained comprising both a mmWave signal and an audio signal.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299]. Further, Ozturk teaches reshaping the input data and representing the input data as a 3D representation during the fusion of the mmWave data and the audio data (i.e., a fusion response diagram.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
Ozturk, however, does not alone teach performing identity recognition based on the fusion response diagram of the living voice signal, wherein performing feature fusion of the living millimeterwave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: tracking and learning effective features of a target by frame streams via a correlation filter, modeling a region of interest, and generating the fusion response diagram of the living voice signal, wherein the target comprises a spectral energy trajectory of the living audio signal or the living millimeter wave signal.
In a similar field of endeavor, (e.g., the verification of users via mmWave voice detection), Lin teaches performing identity recognition based on the fusion response diagram of the living voice signal (see [0028], where determining whether the target audio signal and target mmWave signal original from the target user determined from LPC component as well as based on spectral entropy being greater than a threshold to determine human voice and the multiplication of the mmWave with the audio signal), wherein performing feature fusion of the living millimeterwave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: tracking and learning effective features of a target by frame streams via a correlation filter (see [0072], where VAD is determined based on correlation between mmWave and audio signals), modeling a region of interest, and generating the fusion response diagram of the living voice signal, wherein the target comprises a spectral energy trajectory of the living audio signal or the living millimeter wave signal (see [0018], [0022]-[0026], where determination of human information is determined based on spectral entropy is greater than a threshold (e.g. The examiner interprets the “spectral entropy” to be a function of spectral energy and therefore is the claimed “spectral energy trajectory” since this information is used to determine if human speech is present and once determined [0028] notes the determination using LPC whether the audio is from a target user) (e.g. The Examiner interprets the fusion response diagram to be the multiplication of the mmWave with the audio signal as noted in para [0022]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date to combine the teachings of Ozturk with the teachings of Lin to provide performing identity recognition based on the fusion response diagram. Doing so would have provided a method to detect signals originating from a human when many people are present (see Lin [0155]).
Regarding claim 9, Ozturk-Lin teaches all the limitations of claim 1 as laid out above. Further, Ozturk teaches a computer device, comprising a processor and a memory, the memory storing a computer program, wherein the computer program is executable by the processor to implement the steps of the identity recognition method of claim 1. (Ozturk teaches a computer coupled to a processor that performs a method of voice recognition using mmWave technology. Ozturk at ¶¶ [0078] – [0085].)
Regarding claim 10, Ozturk-Lin teaches all the limitations of claim 9 as laid out above. Further, Ozturk teaches the computer device of claim 9, wherein before the performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring the living millimeter wave signal and the living audio signal, the method further comprises: performing voice activity detection of the millimeter wave signal and the audio signal, and acquiring a millimeter wave signal and an audio signal with voice activity; and (Ozturk teaches performing voice detection and speech recognition using mmWave technology to activate audio recognition (i.e., the mmWave signal and audio signal are retrieved with voice activity detection.) Ozturk at ¶¶ [0436] and [0276] - [0299].)
performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring a denoised millimeter wave signal and a denoised audio signal. (Ozturk contemplates using denoising as a step within preprocessing (see Ozturk at ¶ [0180]). Further, Ozturk discusses preprocessing both the mmWave signal and the audio signal received as demonstrated at Fig. 9. Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
Regarding claim 13, Ozturk-Lin teaches all the limitations of claim 9 as laid out above. Further, Ozturk teaches the computer device of claim 9, wherein the performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring the living millimeter wave signal and the living audio signal further comprises: extracting living feature of millimeter wave and living feature of audio based on the millimeter wave signal and the audio signal, respectively; (Ozturk teaches extracting features of audio signals and radio wave (i.e., mmWave) signals. Ozturk at ¶¶ [0265] - [0273].)
calculating similarity coefficients based on the living feature of millimeter wave and the living feature of audio, and generating a dual-mode reference signal based on the similarity coefficients; and (Ozturk contemplates calculating similarity scores between two vectors of the channel information (i.e., the signal information). Ozturk at ¶¶ [0205] - [0208]. Further, Ozturk teaches processing both mmWave signals and Audio signals to fuse them for masking and speech detection. Ozturk at ¶¶ [0276] - [0299] and Fig. 9. Therefore, the similarity scores calculated for the vectors are used in fusing the mmWave signals and the audio signals. As such, a dual-mode reference signal is output by the fusion operation.)
inputting the dual-mode reference signal into a classification model, and acquiring the living millimeter wave signal and the living audio signal, wherein the classification model is trained by using a standard data set. (Ozturk teaches performing a classification task based on time series data as input (i.e., the channel information takes the form of or includes time-series information as laid out by Ozturk at ¶¶ [0047] - [0050] and [0396] - [0398].). Therefore, Ozturk teaches performing classification on the "dual-mode reference signal" as part of VAD wherein the classification is trained on a standard dataset (Ozturk also teaches training classifiers at ¶¶ [0154] - [0155]. Further still Ozturk teaches training the classifier based on a training time series channel information (TSCI) (i.e., a standard dataset). Ozturk at ¶¶ [0154] - [0155].))
Regarding claim 14, Ozturk-Lin teaches all the limitations of claim 9 as laid out above. Further, Ozturk teaches the computer device of claim 9, wherein the performing feature fusion of the living millimeter wave signal and the living audio signal, and acquiring the fusion response diagram of the living voice signal further comprises: generating a millimeter wave response diagram and an audio response diagram based on the living millimeter wave signal and the living audio signal, respectively; and fusing the millimeter wave response diagram and the audio response diagram, and acquiring the fusion response diagram of the living voice signal. (Ozturk teaches receiving both audio signals and mmWave signals (i.e., a signal is obtained comprising both a mmWave signal and an audio signal.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299]. Further, Ozturk teaches reshaping the input data and representing the input data as a 3D representation during the fusion of the mmWave data and the audio data (i.e., a fusion response diagram.) Ozturk at Fig. 9 and ¶¶ [0276] - [0299]. That is, Ozturk’s fusion and representation of the signals in a 3D representation amount to generating a response diagram and fusing the diagrams of the signals into a single diagram.)
Regarding claim 16, Ozturk-Lin teaches all the limitations of claim 1 as laid out above. Further, Ozturk teaches a computer-readable storage medium having stored a computer program, wherein the computer program is executable by a processor to implement the steps of the identity recognition method of claim 1. (Ozturk teaches a computer coupled to a processor that performs a method of voice recognition using mmWave technology. Ozturk at ¶¶ [0078] – [0085].).
Regarding claim 17, Ozturk-Lin teaches all the limitations of claim 16 as laid out above. Further, Ozturk teaches the computer readable storage medium of claim 16, wherein before the performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring the living millimeter wave signal and the living audio signal, the method further comprises: performing voice activity detection of the millimeter wave signal and the audio signal, and acquiring a millimeter wave signal and an audio signal with voice activity; (Ozturk teaches performing voice detection and speech recognition using mmWave technology to activate audio recognition (i.e., the mmWave signal and audio signal are retrieved with voice activity detection.) Ozturk at ¶¶ [0436] and [0276] - [0299].) and
performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring a denoised millimeter wave signal and a denoised audio signal. (Ozturk contemplates using denoising as a step within preprocessing (see Ozturk at ¶ [0180]). Further, Ozturk discusses preprocessing both the mmWave signal and the audio signal received as demonstrated at Fig. 9. Ozturk at Fig. 9 and ¶¶ [0276] - [0299].1)
Regarding claim 20, Ozturk-Lin teaches all the limitations of claim 16 as laid out above. Further, Ozturk teaches the computer readable storage medium of claim 16, wherein the performing living feature detection based on the millimeter wave signal and the audio signal, and acquiring the living millimeter wave signal and the living audio signal further comprises: extracting living feature of millimeter wave and living feature of audio based on the millimeter wave signal and the audio signal, respectively; (Ozturk teaches extracting features of audio signals and radio wave (i.e., mmWave) signals. Ozturk at ¶¶ [0265] - [0273].)
calculating similarity coefficients based on the living feature of millimeter wave and the living feature of audio, and generating a dual-mode reference signal based on the similarity coefficients; and (Ozturk contemplates calculating similarity scores between two vectors of the channel information (i.e., the signal information). Ozturk at ¶¶ [0205] - [0208]. Further, Ozturk teaches processing both mmWave signals and Audio signals to fuse them for masking and speech detection. Ozturk at ¶¶ [0276] - [0299] and Fig. 9. Therefore, the similarity scores calculated for the vectors are used in fusing the mmWave signals and the audio signals. As such, a dual-mode reference signal is output by the fusion operation.)
inputting the dual-mode reference signal into a classification model, and acquiring the living millimeter wave signal and the living audio signal, wherein the classification model is trained by using a standard data set. (Ozturk teaches performing a classification task based on time series data as input (i.e., the channel information takes the form of or includes time-series information as laid out by Ozturk at ¶¶ [0047] - [0050] and [0396] - [0398].). Therefore, Ozturk teaches performing classification on the "dual-mode reference signal" as part of VAD wherein the classification is trained on a standard dataset (Ozturk also teaches training classifiers at ¶¶ [0154] - [0155]. Further still Ozturk teaches training the classifier based on a training time series channel information (TSCI) (i.e., a standard dataset). Ozturk at ¶¶ [0154] - [0155].))
Claim(s) 3-4, 7, 11-12, 15, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Ozturk in view of Lin as applied to claim 2 above, and further in view of Dong (Secure mmWave Radar Based Speaker Verification for IoT Smart Home).
Regarding claim 3, Ozturk-Lin teaches all the limitations of claim 2. Further, Ozturk teaches the identity recognition method of claim 2, wherein the performing voice activity detection of the millimeter wave signal and the audio signal, and acquiring the millimeter wave signal and the audio signal with voice activity further comprises:
sampling the millimeter wave signal and the audio signal, and acquiring sampled millimeter wave signals and sampled audio signals; (Ozturk teaches sampling the signals and encoding the samples of both audio and radio. Ozturk at ¶¶ [0276] - [0299].)
Furthermore, Lin teaches obtaining a phase of the sampled millimeter wave signals and determining phase difference between sampled millimeter wave signals with the same frequency (see [0089], where phrase difference signal of the mmWave computed).
However, Ozturk in view of Lin do not specifically teach performing low-pass filtering based on the phase difference and the sampled audio.
Dong teaches obtaining a phase of the sampled millimeter wave signals and determining phase difference between sampled millimeter wave signals with the same frequency; (Dong teaches performing phase calculation and determination and calculating the phase difference of mmWave chirps (i.e., sampled mmWave signals of the same frequency.) Dong at § III Preliminary.)
and performing low-pass filtering based on the phase difference and the sampled audio. (Dong also teaches performing low-pass filtering following the phase calculations as part of a digital signal processing step. Dong at § III. Preliminary.)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date to combine the teachings of Ozturk in view of Lin with the teachings of Dong to provide performing identity recognition based on the fusion response diagram. Doing SO would have provided a very high level of accuracy for the system and the detection of replay attacks (i.e., a user playing audio of another user's voice in order to defeat a voice recognition system) as recognized by Dong at section V. Experiments and Evaluation Subsection J. and section VII. Conclusion.
Regarding claim 4, Ozturk-Lin teaches all the limitations of claim 2.
Further still, Ozturk teaches calculating correlation based on the millimeter wave sub-signals and the audio sub- signals, and screening the millimeter wave sub-signals and the audio sub-signals based on the correlation; and (Ozturk teaches aligning and correlating audio and mmWave radar signals based on their matching (i.e., correlating) energy signals based in part on their sample rate. Ozturk at ¶¶ [0276] - [0299]. Further, Ozturk teaches removing specific sentences shorter than specific character lengths based on the collected and correlated audio signals (i.e., the signals are screened.) Ozturk at ¶¶ [0287] - [0299].)
recombining screened millimeter wave sub-signals and screened audio sub-signals, and acquiring the denoised millimeter wave signal and the denoised audio signal. (Ozturk teaches combining encoded audio and radio (i.e., mmWave signals) and denoising the signals. Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
However, Ozturk in view of Lin do not specifically teach performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring the denoised millimeter wave signal and the denoised audio signal further comprises: decomposing the millimeter wave signal and the audio signal with voice activity, and acquiring millimeter wave sub-signals and audio sub-signals.
Dong teaches the identity recognition method of claim 2, wherein the performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring the denoised millimeter wave signal and the denoised audio signal further comprises: decomposing the millimeter wave signal and the audio signal with voice activity, and acquiring millimeter wave sub-signals and audio sub-signals; (Dong teaches decomposing signals into subspaces in part of a processes to determine that the audio is from real human sources and is not reproduced audio. Dong at §§ I. Introduction and IV.C. VCV/LM Signal Extraction).
The Same motivation as applied in claim 3 also applies here.
Regarding claim 7, Ozturk-Lin teach all of the limitations as in claim 1, above.
However, Ozturk-Lin do not specifically teach wherein the performing identity recognition based on the fusion response diagram of the living voice signal further comprises: inputting the fusion response diagram of the living voice signal into an identity recognition network, and acquiring an identity label of the user, wherein the identity recognition network comprises a channel attention module and a spatial attention module
Dong teaches the identity recognition method of claim 1, wherein the performing identity recognition based on the fusion response diagram of the living voice signal further comprises: inputting the fusion response diagram of the living voice signal into an identity recognition network, and acquiring an identity label of the user, wherein the identity recognition network comprises a channel attention module and a spatial attention module. (Dong teaches using a neural network to determine the identity of a speaker based on mmWave signals and Audio signals. Dong at § I. Introduction, IV. Design Method, and Fig. 6.)
The Same motivation as applied in claim 3 also applies here.
Regarding claim 11, Ozturk-Lin teaches all the limitations of claim 10 as noted above.
Further, Ozturk teaches the identity recognition method of claim 2, wherein the performing voice activity detection of the millimeter wave signal and the audio signal, and acquiring the millimeter wave signal and the audio signal with voice activity further comprises:
sampling the millimeter wave signal and the audio signal, and acquiring sampled millimeter wave signals and sampled audio signals; (Ozturk teaches sampling the signals and encoding the samples of both audio and radio. Ozturk at ¶¶ [0276] - [0299].)
Furthermore, Lin teaches obtaining a phase of the sampled millimeter wave signals and determining phase difference between sampled millimeter wave signals with the same frequency (see [0089], where phrase difference signal of the mmWave computed).
However, Ozturk in view of Lin do not specifically teach performing low-pass filtering based on the phase difference and the sampled audio.
Dong teaches obtaining a phase of the sampled millimeter wave signals and determining phase difference between sampled millimeter wave signals with the same frequency; (Dong teaches performing phase calculation and determination and calculating the phase difference of mmWave chirps (i.e., sampled mmWave signals of the same frequency.) Dong at § III Preliminary.)
and performing low-pass filtering based on the phase difference and the sampled audio. (Dong also teaches performing low-pass filtering following the phase calculations as part of a digital signal processing step. Dong at § III. Preliminary.)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date to combine the teachings of Ozturk in view of Lin with the teachings of Dong to provide performing identity recognition based on the fusion response diagram. Doing SO would have provided a very high level of accuracy for the system and the detection of replay attacks (i.e., a user playing audio of another user's voice in order to defeat a voice recognition system) as recognized by Dong at section V. Experiments and Evaluation Subsection J. and section VII. Conclusion.
Regarding claim 12. Ozturk-Lin teaches all the limitations of claim 10 as noted above.
Further still, Ozturk teaches calculating correlation based on the millimeter wave sub-signals and the audio sub- signals, and screening the millimeter wave sub-signals and the audio sub-signals based on the correlation; and (Ozturk teaches aligning and correlating audio and mmWave radar signals based on their matching (i.e., correlating) energy signals based in part on their sample rate. Ozturk at ¶¶ [0276] - [0299]. Further, Ozturk teaches removing specific sentences shorter than specific character lengths based on the collected and correlated audio signals (i.e., the signals are screened.) Ozturk at ¶¶ [0287] - [0299].)
recombining screened millimeter wave sub-signals and screened audio sub-signals, and acquiring the denoised millimeter wave signal and the denoised audio signal. (Ozturk teaches combining encoded audio and radio (i.e., mmWave signals) and denoising the signals. Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
However, Ozturk in view of Lin do not specifically teach performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring the denoised millimeter wave signal and the denoised audio signal further comprises: decomposing the millimeter wave signal and the audio signal with voice activity, and acquiring millimeter wave sub-signals and audio sub-signals.
Dong teaches the identity recognition method of claim 2, wherein the performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring the denoised millimeter wave signal and the denoised audio signal further comprises: decomposing the millimeter wave signal and the audio signal with voice activity, and acquiring millimeter wave sub-signals and audio sub-signals; (Dong teaches decomposing signals into subspaces in part of a processes to determine that the audio is from real human sources and is not reproduced audio. Dong at §§ I. Introduction and IV.C. VCV/LM Signal Extraction).
The Same motivation as applied in claim 3 also applies here.
Regarding claim 15, Ozturk-Lin teaches all the limitations of claim 9 as noted above.
However, Ozturk-Lin do not specifically teach wherein the performing identity recognition based on the fusion response diagram of the living voice signal further comprises: inputting the fusion response diagram of the living voice signal into an identity recognition network, and acquiring an identity label of the user, wherein the identity recognition network comprises a channel attention module and a spatial attention module
Dong teaches the identity recognition method of claim 1, wherein the performing identity recognition based on the fusion response diagram of the living voice signal further comprises: inputting the fusion response diagram of the living voice signal into an identity recognition network, and acquiring an identity label of the user, wherein the identity recognition network comprises a channel attention module and a spatial attention module. (Dong teaches using a neural network to determine the identity of a speaker based on mmWave signals and Audio signals. Dong at § I. Introduction, IV. Design Method, and Fig. 6.)
The Same motivation as applied in claim 3 also applies here.
Regarding claim 18, Ozturk-Lin teaches all the limitations of claim 17 as noted above. Further, Ozturk teaches the identity recognition method of claim 2, wherein the performing voice activity detection of the millimeter wave signal and the audio signal, and acquiring the millimeter wave signal and the audio signal with voice activity further comprises:
sampling the millimeter wave signal and the audio signal, and acquiring sampled millimeter wave signals and sampled audio signals; (Ozturk teaches sampling the signals and encoding the samples of both audio and radio. Ozturk at ¶¶ [0276] - [0299].)
Furthermore, Lin teaches obtaining a phase of the sampled millimeter wave signals and determining phase difference between sampled millimeter wave signals with the same frequency (see [0089], where phrase difference signal of the mmWave computed).
However, Ozturk in view of Lin do not specifically teach performing low-pass filtering based on the phase difference and the sampled audio.
Dong teaches obtaining a phase of the sampled millimeter wave signals and determining phase difference between sampled millimeter wave signals with the same frequency; (Dong teaches performing phase calculation and determination and calculating the phase difference of mmWave chirps (i.e., sampled mmWave signals of the same frequency.) Dong at § III Preliminary.)
and performing low-pass filtering based on the phase difference and the sampled audio. (Dong also teaches performing low-pass filtering following the phase calculations as part of a digital signal processing step. Dong at § III. Preliminary.)
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date to combine the teachings of Ozturk in view of Lin with the teachings of Dong to provide performing identity recognition based on the fusion response diagram. Doing SO would have provided a very high level of accuracy for the system and the detection of replay attacks (i.e., a user playing audio of another user's voice in order to defeat a voice recognition system) as recognized by Dong at section V. Experiments and Evaluation Subsection J. and section VII. Conclusion.
Regarding claim 19, Ozturk-Lin teaches all the limitations of claim 17 as noted above. Further still, Ozturk teaches calculating correlation based on the millimeter wave sub-signals and the audio sub- signals, and screening the millimeter wave sub-signals and the audio sub-signals based on the correlation; and (Ozturk teaches aligning and correlating audio and mmWave radar signals based on their matching (i.e., correlating) energy signals based in part on their sample rate. Ozturk at ¶¶ [0276] - [0299]. Further, Ozturk teaches removing specific sentences shorter than specific character lengths based on the collected and correlated audio signals (i.e., the signals are screened.) Ozturk at ¶¶ [0287] - [0299].)
recombining screened millimeter wave sub-signals and screened audio sub-signals, and acquiring the denoised millimeter wave signal and the denoised audio signal. (Ozturk teaches combining encoded audio and radio (i.e., mmWave signals) and denoising the signals. Ozturk at Fig. 9 and ¶¶ [0276] - [0299].)
However, Ozturk in view of Lin do not specifically teach performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring the denoised millimeter wave signal and the denoised audio signal further comprises: decomposing the millimeter wave signal and the audio signal with voice activity, and acquiring millimeter wave sub-signals and audio sub-signals.
Dong teaches the identity recognition method of claim 2, wherein the performing denoising of the millimeter wave signal and the audio signal with voice activity, and acquiring the denoised millimeter wave signal and the denoised audio signal further comprises: decomposing the millimeter wave signal and the audio signal with voice activity, and acquiring millimeter wave sub-signals and audio sub-signals; (Dong teaches decomposing signals into subspaces in part of a processes to determine that the audio is from real human sources and is not reproduced audio. Dong at §§ I. Introduction and IV.C. VCV/LM Signal Extraction).
The Same motivation as applied in claim 3 also applies here.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Zhang et al. (“AmbiEar: mmWave Based Voice Recognition in NLoS Scenarios”) is cited to disclose using mmWave and voice for voice recognition.
Ozturk (“RADIOSES: mmWave-Based Audioradio Speech Enhancement and Separation System”) is cited to disclose usage of mmWave and audio to localize and separate speakers (see Figure 1).
Li et al. (“VocalPrint: Exploring A Resilient and Secure Voice Authentication via mmWave Biometric Interrogation”) is cited to disclose voice authentication using mmWave in order to identify a speaker (see Figure 1, 5).
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PARAS D SHAH whose telephone number is (571)270-1650. The examiner can normally be reached Monday-Thursday 7:30AM-2:30PM, 5PM-7PM (EST), Friday 8AM-noon (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.
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.
/Paras D Shah/ Supervisory Patent Examiner, Art Unit 2653
07/31/2026
Prosecution Insights