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 .
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Mohammad et al (20240282327) in view of Lee et al (20160163304) .
As per claim 1, Mohammad et al (20240282327) teaches a method for in-vehicle noise-pattern learning for voice applications (as noise prediction for noise removal in speech – para 0028-0029; and applied to vehicle environments – para 0043 – “integrated into a vehicle”), comprising:
embedding multimodal data from environment and vehicle data (as, combining predicted noise/subtracted noise – para 0039, 0040, with mode data of the vehicle – para 0055);
embedding acoustic data from microphone-captured data in a cabin of the vehicle (as integrating the mode data with acoustic data from the microphone – para 0056-0057);
concatenating the embeddings to form a latent vector characterizing the embeddings (as, producing a latent vector combining features of the detected audio signal – para 0076, which list the audio signal features, including “other data representing a time-windowed portion of the input audio signal”; the “other data” includes noise prediction derived from the audio signal – see mode data – para 0055-0056);
and identifying a noise type
As per claim 1, Mohammad et al (20240282327) teaches the measurement of audio signals using a plethora of well known techniques, such as spectral measurements, as well as time-based measurements – see para 0076; but does not explicitly teach the use of mean/variance parameters as part of the feature vector space. Lee et al (20160163304) teaches active noise control in a vehicle (para 0004), using mean/variance calculations to control the noise at certain thresholds – see para 0022, using least-mean-square measurement, for noise estimates, and variance calculations to set the noise threshold measurement – para 0038-0039. Therefore, it would have been obvious to one of ordinary skill in the art of noise estimation and filtering, to include in the feature vector space of audio signal measurements of Mohammad et al (20240282327), the additional measurement of mean and variance as part of the noise estimate feature vectors (as part of the processing, of the entire processing calculation – see fig. 1 of Lee et al (20160163304)), as taught by Lee et al (20160163304), because it would advantageously handle impulse-transient type signals, as well as stationary signals, without too much further computational complexity – Lee et al (20160163304), para 0027.
As per claim 2, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches the method of claim 1, wherein: the environment data comprises weather data, road segment roughness, road disruption scores, or location-based application programming interfaces (APIs) (see Mohammad et al (20240282327), para 0108 – using an app to set a destination – thereby, explicitly teaching, GPS location functions; and “display weather forecast”), and the vehicle data comprises speed, engine revolutions-per-minute (RPM), engine temperature, turn signals on or off, windows up or down, sunroof open or closed, or honking a horn in the vehicle (see Mohammad et al (20240282327) teaching tracking, wipes movement, window open/closed – para 0055).
As per claim 3, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches the method of claim 1, wherein identifying the noise type comprises calculating an inter-quartile range (IQR) of the mean and variance of the latent vector as measures of dispersion for both the mean and variance within a calibratable time window (see Lee et al (20160163304), calculating IQR’s – para 0039 –0041, to determine which quartile the vector of data resides – para0040, as part of the threshold calculations – para 0039, which used the mean/variance calculations – see para 0004, 0012, 0013).
As per claim 4, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches the method of claim 3, further comprising producing fine-grained noise type identification based on the calculated IQR and the adaptive time window (see Lee et al (20160163304), as using the IQR/quartile percentages - - para 0040, 0041 with a sliding window – para 0043 – mapping to ‘adaptive time window’; all to estimate the noise – para 0051).
As per claim 5, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches the method of claim 4, wherein fine-grained noise type identification comprises one or more of stationary mean and stationary variance; non-stationary mean and stationary variance; stationary mean and non-stationary variance; or non-stationary mean and non-stationary variance (See Lee et al (20160163304) , as applied above, to the variance calculations to determine thresholds in the noise estimates; Lee et al (20160163304) also addresses stationary-type noise – para 0017, as well as non-stationary (ie, equivalent to impulse/transient type signals – see para 0024 – 0025 – “impulsive samples”, “the impulses…may still have adverse influence on the filter weight”).
As per claim 6, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches the method of claim 4, wherein the adaptive time window is based on one or more of an inverse logistic function, a reverse sigmoid function, or a combined mean IQR and variance IQR (see Lee et al (20160163304), with the sliding window – para 0043, is based on IQR calculations – para 0039-0042).
As per claim 7, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches the method of claim 1, wherein the identified noise types are used for in-vehicle voice applications including at least one of active noise cancellation or speech enhancement (see Mohammad et al (20240282327), teaching speech enhancement – para 0003, 0035; para 0102 active noise cancellation) as well as Lee et al (20160163304) teaching active noise cancellation techniques – para 0004, para 0017.
Claims 8-14 are vehicle claims that perform the steps found in method claims 1-7 above and as such, claims 8-14 are similar in scope and content to claims 1-7 above; therefore, claims 8-14 are rejected under similar rationale as presented against claims 1-7. Furthermore, both references teach the noise modeling/measurements to be in a vehicle environment -- Mohammad et al (20240282327) see para 0043, and Lee et al (20160163304) para 0047.
Claims 15-19 are system claims that perform the steps found in method claims 1-7 above and as such, claims 15-19 are similar in scope and content to claims 1-7 above; therefore, claims 15-19 are rejected under similar rationale as presented against claims 1-7. Furthermore, both references teach the noise modeling/measurements to be in a vehicle environment -- Mohammad et al (20240282327) see para 0043, and Lee et al (20160163304) para 0047.
As per claim 20, see rationale as presented above, to address claim 15, from which claim 20 depends. Further to claim 20, the combination of Mohammad et al (20240282327) in view of Lee et al (20160163304) teaches denoising (Mohammad et al (20240282327) – para 0029).
Response to Arguments
Applicant's arguments filed 08/04/2025 have been fully considered but they are not persuasive. Applicant’s detailed addressing of the applied prior art begins on pp 8 of the response. As to applicants allegation that the Mohoamad (sp?) reference does not mention an adaptive time window, examiner notes that 1) the claim scope is toward an ‘using an adaptive time window’ and being “fine-grained via the adaptive time window” is descriptive in nature, without an explicit claim scope on what parameters the time window is being adapted (and further evidenced by applicants’ referral to applicants specification, para 0046). In response to applicant's argument toward the use of the adaptive time window, a recitation of the intended use of the claimed invention must result in a structural difference between the claimed invention and the prior art in order to patentably distinguish the claimed invention from the prior art. If the prior art structure is capable of performing the intended use, then it meets the claim. Examiner notes, in para 0077 of Mohammad, various types of spectral features are extracted, using time-windowing for that particular calculation:
See para 0077 -- e.g., a complex spectrum, a magnitude spectrum, a mel spectrum, a bark spectrum, etc.), cepstral features of a time-windowed portion of the input audio signal 320 (e.g., mel frequency cepstral coefficients, bark frequency cepstral coefficients, etc.), or other data representing a time-windowed portion of the input audio signal 320.
Furthermore, examiner notes that it is very old and notoriously well known, in the art of audio signal processing, to modify/vary the time window when using various processing transforms, such flexibility disclosed in Mohammad; e.g., see:
Gemello et al (20030191640):
[0041] The possibility of enlarging the window N makes it possible to exploit variable time and frequency resolution, described in detail below, which is characteristic of wavelet development with respect to the simple Fourier transform.
Li et al (20060101060):
(para 0014) -- proposed to transform the time sequence to the frequency domain by using DFT (Discrete Fourier Transform) and wavelets to reduce dimensions. For subsequence matching, solutions include I-adaptive index to solve the matching problem for searches of pre-specified lengths, PAA (Piecewise Aggregate Approximation) technique to average values of equal-size windows of the time sequence or APCA (Adaptive Piecewise Constant Approximation) to average values of variable-size windows of the time sequence of the time sequence, and a multi-resolution index data structure.
(para 0082) -- Common audio features include power, spectral centroid and rolloff (measures of the relative brightness of sound), spectral flux (a measure of the frame-to-frame variance in spectral shape), zero crossing rate (noisiness), and Mel-Frequency Cepstral Coefficients (MFCCs), which is a compact representation of spectral shape.
Clearly, the general concept of adapting the time window according to the signal, is old and notoriously well know; and with the Mohammad et al (20240282327) reference teaching various signal processing techniques, one of ordinary skill in the art would easily recognize the advantage of adapting the time window according to the signal/type being processed. Furthermore, in response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies, applicants specification para 0046, are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Applicants point to para 0022 of the specification as to the definition of granularity/’fine-grained” – examiner notes, that this is not the only citation in applicants specification towards “fine-grained” – examiner reminds applicant that the claim scope is interpreted under Broadest Reasonable Interpretation, the definition of fine-grained – e.g., para 0004, ‘being fine-grained via the adaptive time window’, as well as para 0024. Examiner recommends, to actively claim, “adapting the time window at a higher bit rate, said higher bitrate producing a higher resolution”. Examiner further notes, that the above references teach modifying the time window as to, affect, higher/lower resolution. As to applicants arguments against variance/mean of the latent vector, examiner notes that applicant finds a recitation to Lee et al (20160163304) towards median, but the referred to sections by examiner, points to a mean-square-error calculation (and notes, a mean/averaging calculation is performed in lms). Also, likewise above in the discussion of the variable time window, examiner notes that is old and notoriously well known in the art, to perform mean/averaging of the parameters: see Li et al (20060101060):
(para 0014) -- proposed to transform the time sequence to the frequency domain by using DFT (Discrete Fourier Transform) and wavelets to reduce dimensions. For subsequence matching, solutions include I-adaptive index to solve the matching problem for searches of pre-specified lengths, PAA (Piecewise Aggregate Approximation) technique to average values of equal-size windows of the time sequence or APCA (Adaptive Piecewise Constant Approximation) to average values of variable-size windows of the time sequence of the time sequence, and a multi-resolution index data structure.
Examiner recommends further claim amendments overcome the teachings of the prior art of record, including the evidence provided of, old and notoriously well known in the art of audio processing.
Conclusion
THIS ACTION IS MADE FINAL. 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. Please see related art listed on the PTO-892 form.
Furthermore, the following references were found, that can be applicable to certain claim features, as well as applicants specification:
Gemello et al (20030191640):
[0041] The possibility of enlarging the window N makes it possible to exploit variable time and frequency resolution, described in detail below, which is characteristic of wavelet development with respect to the simple Fourier transform.
Li et al (20060101060):
(para 0014) -- proposed to transform the time sequence to the frequency domain by using DFT (Discrete Fourier Transform) and wavelets to reduce dimensions. For subsequence matching, solutions include I-adaptive index to solve the matching problem for searches of pre-specified lengths, PAA (Piecewise Aggregate Approximation) technique to average values of equal-size windows of the time sequence or APCA (Adaptive Piecewise Constant Approximation) to average values of variable-size windows of the time sequence of the time sequence, and a multi-resolution index data structure.
(para 0082) -- Common audio features include power, spectral centroid and rolloff (measures of the relative brightness of sound), spectral flux (a measure of the frame-to-frame variance in spectral shape), zero crossing rate (noisiness), and Mel-Frequency Cepstral Coefficients (MFCCs), which is a compact representation of spectral shape.
Venkatesh et al (7171003) teaches acoustic echo and noise cancellation in a vehicle cabin (see abstract, Fig. 2,12).
Fridman et al (20220324290) teaches vehicle (Figure 7) extracting features from the measured signals (fig. 6) to perform active acoustic control – Fig. 6, subblock 632.
Jung et al (2023/0160853) teaches tracking vehicle noise and tying to a vehicle type recognition model – fig. 7.
Honkala (20220027709) teaches machine learning based, denoising, detecting noise types (para 009) that can be used in vehicle environments (para 0042).
Li et al (20220206130) teaches the use of neural networks to operate on condensed latent vectors that are concatenated with noise vectors (para 0026) in vehicle environments – para 0025, 0002.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael Opsasnick, telephone number (571)272-7623, who is available Monday-Friday, 9am-5pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Mr. Richemond Dorvil, can be reached at (571)272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of 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).
/Michael N Opsasnick/Primary Examiner, Art Unit 2658 10/30/2025
Prosecution Insights