# US 12,762,229 B2 · Presentation attacks in reverberant conditions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,762,229 B2 - Document ID: US12762229B2 - Status: Granted - Kind: B2 - Application number: 18/598,595 - Filed: 2024-03-07 - Published: 2024-09-19 - Granted: 2026-10-13 - Earliest claimed: 2023-03-15 - Assignees: Pindrop Security, Inc. - Applicants: Pindrop Security, Inc. - Inventors: Nikolay Gaubitch; David Looney - Web page: https://patentgrep.com/patent/US12762229B2 ## CPC - G06F 21/554: {involving event detection and direct action} - G06N 20/00: Machine learning - G10L 25/18: the extracted parameters being spectral information of each sub-band - G10L 25/51: for comparison or discrimination - G10L 25/69: for evaluating synthetic or decoded voice signals - G06F 2221/034: Test or assess a computer or a system - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Embodiments include a computing device that executes software routines and/or one or more machine-learning architectures including obtaining training audio signals having corresponding training impulse responses associated with reverberation degradation, training a machine-learning model of a presentation attack detection engine to generate one or more acoustic parameters by executing the presentation attack detection engine using the training impulse responses of the training audio signals and a loss function, obtaining an audio signal having an acoustic impulse response associated with reverberation degradation caused by one or more rooms, generating the one or more acoustic parameters for the audio signal by executing the machine-learning model using the audio signal as input, and generating an attack score for the audio signal based upon the one or more parameters generated by the machine-learning model. ## Claims ### Claim 1 A computer-implemented method comprising: obtaining, by a computer, a plurality of training audio signals having corresponding training acoustic impulse responses including at least one single-room training acoustic impulse response and at least one combined multi-room training acoustic impulse response corresponding to the training acoustic impulse responses from two or more rooms; training, by the computer, a parameter estimation machine-learning model of a presentation attack detection (PAD) engine to estimate one or more acoustic parameters by executing the parameter estimation machine-learning model of the PAD engine using the training acoustic impulse responses of the plurality of training audio signals and a loss function using a plurality of training labels corresponding to the training audio signals, each training label indicating one or more training acoustic parameters for the training acoustic impulse response in the corresponding training audio signal; obtaining, by the computer, an audio signal having an acoustic impulse response caused by one or more rooms, the acoustic impulse response of the audio signal including at least one of a single room acoustic impulse response or a combined multi-room acoustic impulse response; and generating, by the computer, the one or more acoustic parameters for the audio signal by executing the parameter estimation machine-learning model using the audio signal as input. ### Claim 2 (depends on 1) The method according to claim 1, further comprising generating, by the computer, an attack score for the audio signal based upon the one or more acoustic parameters by executing a PAD scoring machine-learning model of the PAD engine, the attack score indicating a likelihood that the acoustic impulse response of the audio signal is caused by two or more rooms. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, further comprising detecting, by the computer, that the audio signal is a presentation attack in response to determining that the attack score satisfies an attack score threshold. ### Claim 4 (depends on 2) The computer-implemented method of claim 2, wherein generating the attack score for the audio signal includes determining, by the computer, whether the acoustic impulse response of the audio signal is consistent throughout the audio signal. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, further comprising segmenting, by the computer, the audio signal into a plurality of frames, wherein the computer executes the PAD engine using each frame of the audio signal as input to the presentation attack engine. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising transforming, by the computer, the audio signal into a spectral domain representation, wherein the computer executes the PAD engine using the spectral representation of the audio signal as input to the PAD engine. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the one or more acoustic parameters include at least one of: spectral standard deviation, late reverberation onset, SNR, or energy decay curve. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, further comprising extracting, by the computer, a feature vector for the one or more acoustic parameters of the acoustic impulse response of the audio signal. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein obtaining the plurality of training audio signals includes generating, by the computer, one or more of the plurality of training audio signals according to a simulated environment. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein the acoustic impulse response of the audio signal is a type of acoustic impulse response not represented in the training audio signals. ### Claim 11 A non-transitory computer-readable medium comprising machine-executable instructions which, when executed by one or more processors, cause the one or more processors to: obtain a plurality of training audio signals having corresponding training acoustic impulse responses including at least one single-room training acoustic impulse response and at least one combined multi-room training acoustic impulse response corresponding to the training acoustic impulse responses from two or more rooms; train a parameter estimation machine-learning model of a presentation attack detection (PAD) engine to estimate one or more acoustic parameters by executing the parameter estimation machine-learning model of the PAD engine using the training acoustic impulse responses of the plurality of training audio signals and a loss function using a plurality of training labels corresponding to the training audio signals, each training label indicating one or more training acoustic parameters for the training acoustic impulse response in the corresponding training audio signal; obtain an audio signal having an acoustic impulse response caused by one or more rooms, the acoustic impulse response of the audio signal including at least one of a single room acoustic impulse response or a combined multi-room acoustic impulse response; and generate the one or more acoustic parameters for the audio signal by executing the machine-learning model using the audio signal as input. ### Claim 12 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions further cause the one or more processors to generate an attack score for the audio signal based upon the one or more acoustic parameters by executing a PAD scoring machine-learning model of the PAD engine, the attack score indicating a likelihood that the acoustic impulse response of the audio signal is caused by two or more rooms. ### Claim 13 (depends on 12) The non-transitory computer-readable medium of claim 12, wherein the instructions further cause the one or more processors to detect that the audio signal is a presentation attack in response to determining that the attack score satisfies an attack score threshold. ### Claim 14 (depends on 12) The non-transitory computer-readable medium of claim 12, wherein, when generating the attack score for the audio signal, the instructions further cause the one or more processors to determine whether the acoustic impulse response of the audio signal is consistent throughout the audio signal. ### Claim 15 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions further cause the one or more processors to segment the audio signal into a plurality of frames, and execute the PAD engine using each frame of the audio signal as input to the presentation attack engine. ### Claim 16 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions further cause the one or more processors to transform the audio signal into a spectral domain representation, and execute the PAD engine using the spectral representation of the audio signal as input to the PAD engine. ### Claim 17 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the one or more acoustic parameters include at least one of: spectral standard deviation, late reverberation onset, SNR, or energy decay curve. ### Claim 18 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the instructions further cause the one or more processors to extract a feature vector for the one or more acoustic parameters of the acoustic impulse response of the audio signal. ### Claim 19 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein, when obtaining the plurality of training audio signals, the instructions further cause the one or more processors to generate one or more of the plurality of training audio signals in a simulated environment. ### Claim 20 (depends on 11) The non-transitory computer-readable medium of claim 11, wherein the acoustic impulse response of the audio signal is a type of acoustic impulse response not represented in the training audio signals.