Abstract: In an embodiment, a system includes a first sensor sensing brain signal data from a user, the brain signal data including nerve signals transmitted via a brain of the user and corresponding to a first set of words spoken by the user. The system also includes a second sensor sensing audio data from the user corresponding to the first set of words and one or more processors communicatively coupled to the first sensor and the second sensor. In the embodiment, the one or more processors generate text data based on the audio data using a machine learning algorithm and re-train the machine learning algorithm based on the brain signal data and the text data to generate a re-trained machine learning algorithm, wherein the re-trained machine learning algorithm generates second text data associated with a second set of words based on second brain signal data.

Abstract: Apparatus, systems, methods, and articles of manufacture are disclosed for acoustic signal processing adaptive to microphone distances. An example system includes a microphone to convert an acoustic signal to an electrical signal and one or more processors to: estimate a distance between a source of the acoustic signal and the microphone; select a signal processing mode based on the distance; and process the electrical signal in accordance with the selected processing mode.

Abstract: A system, article, device, apparatus, and method of audio processing comprises receiving, by processor circuitry, audible audio signal data of intermodulation distortion products (IDPs) based on ultrasonic audio signals received by at least one microphone of an audio device. The method also compares the audible audio signal data to ultrasonic audio signal data of the ultrasonic audio signals. Thereafter, the method determines a plurality of susceptibility values each of a different ultrasonic frequency based on the comparing, wherein the plurality of susceptibility values represent an ultrasonic attack susceptibility of the audio device.

Abstract: A system, article, device, apparatus, and method for a multi-microphone audio signal unifier comprises receiving, by processor circuitry, an initial audio signal from one of multiple microphones arranged to provide the initial audio signal. This also includes modifying the initial audio signal comprising using at least one neural network (NN) to generate a unified audio signal that is more generic to a type of microphone than the initial audio signal.

Abstract: Apparatus, systems, methods, and articles of manufacture are disclosed for acoustic signal processing adaptive to microphone distances. An example system includes a microphone to convert an acoustic signal to an electrical signal and one or more processors to: estimate a distance between a source of the acoustic signal and the microphone; select a signal processing mode based on the distance; and process the electrical signal in accordance with the selected processing mode.

Abstract: A user computing device includes a microphone to generate an audio signal and a self-noise silencer to generate a feature set corresponding to the audio signal, where the input feature identifies, for each of a plurality of frequency components in the audio signal, a respective magnitude value. At least a portion of the feature set is provided as an input to a machine learning model trained to infer frequencies contributing to self-noise generated at the microphone. An attenuation mask is generated, based on an output of the machine learning model, that identifies an attenuation value for at least a subset of the plurality of frequency components. The attenuation mask is applied to at least the subset of the magnitude values of the plurality of frequency components to remove self-noise from the audio signal and generate a denoised version of the audio signal.

Abstract: Techniques are provided for detection of laser-based audio injection attacks. A methodology implementing the techniques according to an embodiment includes calculating cross correlations between signals received from microphones of an array of two or more microphones. The method also includes identifying time delays associated with peaks of the cross correlations, and magnitudes associated with the peaks of the cross correlations. The method further includes calculating a time alignment metric based on the time delays and calculating a similarity metric based on the magnitudes. The method further includes generating a first attack indicator based on a comparison of the time alignment metric to a first threshold and generating a second attack indicator based on a comparison of the similarity metric to a second threshold. The method further includes providing warning of a laser-based audio attack based on the first attack indicator and/or the second attack indicator.

Abstract: Techniques are provided for audio capture path evaluation of microphones incorporated into a device under test (DUT). A methodology implementing the techniques according to an embodiment includes estimating impulse responses (IRs) of the DUT microphones based on a comparison of a test audio signal received through the DUT microphones, at a selected measurement angle, to the test audio signal received through a reference microphone. The method also includes calculating group delays for the DUT microphones based on phase responses of the estimated IRs and calculating an average of the group delays. The method further includes calculating a distance, projected onto the measurement angle, between the DUT microphones and a geometric center of the DUT microphones. The distance is calculated as a product of the speed of sound and a difference between the average delay and the group delays for the DUT microphones. The process is repeated for additional measurement angles.

Abstract: Techniques are provided for audio-based detection and tracking of an acoustic source. A methodology implementing the techniques according to an embodiment includes generating acoustic signal spectra from signals provided by a microphone array, and performing beamforming on the acoustic signal spectra to generate beam signal spectra, using time-frequency masks to reduce noise. The method also includes detecting, by a deep neural network (DNN) classifier, an acoustic event, associated with the acoustic source, in the beam signal spectra. The DNN is trained on acoustic features associated with the acoustic event. The method further includes performing pattern extraction, in response to the detection, to identify time-frequency bins of the acoustic signal spectra that are associated with the acoustic event, and estimating a motion direction of the source relative to the array of microphones based on Doppler frequency shift of the acoustic event calculated from the time-frequency bins of the extracted pattern.

Abstract: A method of audio device performance testing generates virtual audio device data packages.

Abstract: Apparatus, systems, methods, and articles of manufacture are disclosed for acoustic signal processing adaptive to microphone distances. An example system includes a microphone to convert an acoustic signal to an electrical signal and one or more processors to: estimate a distance between a source of the acoustic signal and the microphone; select a signal processing mode based on the distance; and process the electrical signal in accordance with the selected processing mode.

Abstract: In an embodiment, a system includes a first sensor sensing brain signal data from a user, the brain signal data including nerve signals transmitted via a brain of the user and corresponding to a first set of words spoken by the user. The system also includes a second sensor sensing audio data from the user corresponding to the first set of words and one or more processors communicatively coupled to the first sensor and the second sensor. In the embodiment, the one or more processors generate text data based on the audio data using a machine learning algorithm and re-train the machine learning algorithm based on the brain signal data and the text data to generate a re-trained machine learning algorithm, wherein the re-trained machine learning algorithm generates second text data associated with a second set of words based on second brain signal data.

Abstract: Techniques are provided for detection of laser-based audio injection attacks. A methodology implementing the techniques according to an embodiment includes calculating cross correlations between signals received from microphones of an array of two or more microphones. The method also includes identifying time delays associated with peaks of the cross correlations, and magnitudes associated with the peaks of the cross correlations. The method further includes calculating a time alignment metric based on the time delays and calculating a similarity metric based on the magnitudes. The method further includes generating a first attack indicator based on a comparison of the time alignment metric to a first threshold and generating a second attack indicator based on a comparison of the similarity metric to a second threshold. The method further includes providing warning of a laser-based audio attack based on the first attack indicator and/or the second attack indicator.

Abstract: Techniques are provided for audio capture path evaluation of microphones incorporated into a device under test (DUT). A methodology implementing the techniques according to an embodiment includes estimating impulse responses (IRs) of the DUT microphones based on a comparison of a test audio signal received through the DUT microphones, at a selected measurement angle, to the test audio signal received through a reference microphone. The method also includes calculating group delays for the DUT microphones based on phase responses of the estimated IRs and calculating an average of the group delays. The method further includes calculating a distance, projected onto the measurement angle, between the DUT microphones and a geometric center of the DUT microphones. The distance is calculated as a product of the speed of sound and a difference between the average delay and the group delays for the DUT microphones. The process is repeated for additional measurement angles.

Abstract: Techniques are provided for detection of laser-based audio injection attacks through classification of the acoustic environment. A methodology implementing the techniques according to an embodiment includes broadcasting a reference signal over a loudspeaker into a local environment, and generating a reference model of the local environment based on analysis of a transformed version of that reference signal received through a microphone of the device. The method further includes generating an estimate model based on analysis of a segment of speech in an audio signal received through the microphone. The estimate model is associated with an environment in which the speech was generated. The method further includes calculating a similarity metric (e.g., mathematical distance) between the reference model and the estimate model, and providing warning of a laser-based audio attack if the similarity metric exceeds a threshold value associated with an attack.

Abstract: Techniques are provided for audio-based detection and tracking of an acoustic source. A methodology implementing the techniques according to an embodiment includes generating acoustic signal spectra from signals provided by a microphone array, and performing beamforming on the acoustic signal spectra to generate beam signal spectra, using time-frequency masks to reduce noise. The method also includes detecting, by a deep neural network (DNN) classifier, an acoustic event, associated with the acoustic source, in the beam signal spectra. The DNN is trained on acoustic features associated with the acoustic event. The method further includes performing pattern extraction, in response to the detection, to identify time-frequency bins of the acoustic signal spectra that are associated with the acoustic event, and estimating a motion direction of the source relative to the array of microphones based on Doppler frequency shift of the acoustic event calculated from the time-frequency bins of the extracted pattern.

Abstract: For a multiple microphone system, a phase response mismatch may be corrected. One embodiment includes receiving audio from a first microphone and from a second microphone, the microphones being coupled to a single device for combining the received audio, recording the received audio from the first microphone and the second microphone before combining the received audio, detecting a phase response mismatch in the recording at the device between the audio received at the second microphone and the audio received at the first microphone, if a phase response mismatch is detected, then estimating a phase delay between the second microphone and the first microphone, and storing the estimated phase delay for use in correcting the phase delay in received audio before combining the received audio.

Abstract: A mechanism is described for facilitating automatic gain adjustment in audio systems according to one embodiment. A method of embodiments, as described herein, includes determining status of one or more of gain settings, mute settings, and boost settings associated with one or more microphones based on a configuration of a computing device including a voice-enabled device. The method may further comprise recommending adjustment of microphone gain based on the configuration and the status of one or more of the gain, mute, and boost settings, and applying the recommended adjustment of the microphone gain.

Abstract: System and techniques for automatic gain control for speech recognition are described herein. An audio signal may be obtained. A signal-to-noise ratio (SNR) may be derived from the audio signal. The SNR may be compared to a threshold. A stored gain value may be updated when the SNR is beyond the threshold and the stored gain value may be applied to a descendant (e.g., later) of the audio signal otherwise.

Abstract: Techniques are provided for defending against an ultrasonic attack on a speech enabled device. A methodology implementing the techniques according to an embodiment includes detecting voice activity in an audio signal received by the device and generating an ultrasonic jamming signal in response to the detection. The jamming signal is broadcast over a loudspeaker for up to the duration of the detected voice activity to defend against the ultrasonic attack. According to another embodiment, the ultrasonic jamming signal is generated in response to detection of a wake-on-voice key phrase in the received audio signal, and the jamming signal is broadcast over the loudspeaker for a time duration selected to be less than or equal to a time window during which spoken commands are accepted by the device following the wake-on-voice key phrase detection. The jamming signal may include white or colored noise, combinations of tones, and/or a periodic sweep frequency.