Apple Inc.

Ante Jukic

Mehrez Souden

Joshua D Atkins

Symeon Delikaris Manias

Jason Wung

Ramin Pishehvar

Ashrith Deshpande

Matthew S Connolly

Sabine Webel

Ronald J Guglielmone, Jr

John Woodruff

Sarmad Aziz Malik

Feipeng Li

Feiping Li

An audio processing device may generate a plurality of microphone signals from a plurality of microphones of the audio processing device. The audio processing device may determine a gaze of a user who is wearing a playback device that is separate from the audio processing device, the gaze of the user being determined relative to the audio processing device. The audio processing device may extract speech that correlates to the gaze of the user, from the plurality of microphone signals of the audio processing device by applying the plurality of microphone signals of the audio processing device and the gaze of the user to a machine learning model. The extracted speech may be played to the user through the playback device.

Machine learning and user driven selective hearing

An audio renderer can have a machine learning model that jointly processes audio and visual information of an audiovisual recording. The audio renderer can generate output audio channels. Sounds captured in the audiovisual recording and present in the output audio channels are spatially mapped based on the joint processing of the audio and visual information by the machine learning model. Other aspects are described.

Audio renderer based on audiovisual information

Disclosed is a multi-task machine learning model such as a time-domain deep neural network (DNN) that jointly generate an enhanced target speech signal and target audio parameters from a mixed signal of target speech and interference signal. The DNN may encode the mixed signal, determine masks used to jointly estimate the target signal and the target audio parameters based on the encoded mixed signal, apply the mask to separate the target speech from the interference signal to jointly estimate the target signal and the target audio parameters, and decode the masked features to enhance the target speech signal and to estimate the target audio parameters. The target audio parameters may include a voice activity detection (VAD) flag of the target speech. The DNN may leverage multi-channel audio signal and multi-modal signals such as video signals of the target speaker to improve the robustness of the enhanced target speech signal.

End-to-end time-domain multitask learning for ML-based speech enhancement

A plurality of microphone signals can be captured with a plurality of microphones of the device. One or more echo dominant audio signals can be determined based on a pick-up beam directed towards one or more speakers of a playback device. Sound that is emitted from the one or more speakers and sensed by the plurality of microphones can be removed from plurality of microphone signals, by using the one or more echo dominant audio signals as a reference, resulting in clean audio.

Spatially informed acoustic echo cancelation

A device implementing a system for processing speech in an audio signal includes at least one processor configured to receive an audio signal corresponding to at least one microphone of a device, and to determine, using a first model, a first probability that a speech source is present in the audio signal. The at least one processor is further configured to determine, using a second model, a second probability that an estimated location of a source of the audio signal corresponds to an expected position of a user of the device, and to determine a likelihood that the audio signal corresponds to the user of the device based on the first and second probabilities.

Spatially informed audio signal processing for user speech

A device for processing audio signals in a time-domain includes a processor configured to receive multiple audio signals corresponding to respective microphones of at least two or more microphones of the device, at least one of the multiple audio signals comprising speech of a user of the device. The processor is configured to provide the multiple audio signals to a machine learning model, the machine learning model having been trained based at least in part on an expected position of the user of the device and expected positions of the respective microphones on the device. The processor is configured to provide an audio signal that is enhanced with respect to the speech of the user relative to the multiple audio signals, wherein the audio signal is a waveform output from the machine learning model.

Microphone array based deep learning for time-domain speech signal extraction

A hybrid machine learning-based and DSP statistical post-processing technique is disclosed for voice activity detection. The hybrid technique may use a DNN model with a small context window to estimate the probability of speech by frames. The DSP statistical post-processing stage operates on the frame-based speech probabilities from the DNN model to smooth the probabilities and to reduce transitions between speech and non-speech states. The hybrid technique may estimate the soft decision on detected speech in each frame based on the smoothed probabilities, generate a hard decision using a threshold, detect a complete utterance that may include brief pauses, and estimate the end point of the utterance. The hybrid voice activity detection technique may incorporate a target directional probability estimator to estimate the direction of the speech source. The DSP statistical post-processing module may use the direction of the speech source to inform the estimates of the voice activity.

Hybrid learning-based and statistical processing techniques for voice activity detection

A learning based system such as a deep neural network (DNN) is disclosed to estimate a distance from a device to a speech source. The deep learning system may estimate the distance of the speech source at each time frame based on speech signals received by a compact microphone array. Supervised deep learning may be used to learn the effect of the acoustic environment on the non-linear mapping between the speech signals and the distance using multi-channel training data. The deep learning system may estimate the direct speech component that contains information about the direct signal propagation from the speech source to the microphone array and the reverberant speech signal that contains the reverberation effect and noise. The deep learning system may extract signal characteristics of the direct signal component and the reverberant signal component and estimate the distance based on the extracted signal characteristics using the learned mapping.

Learning-based distance estimation

An echo canceller is disclosed in which audio signals of the playback content received by one or more of the microphones from a loudspeaker of the device may be used as the playback reference signals to estimate the echo signals of the playback content received by a target microphone for echo cancellation. The echo canceller may estimate the transfer function between a reference microphone and the target microphone based on the playback reference signal of the reference microphone and the signal of the target microphone. To mitigate near-end speech cancellation at the target microphone, the echo canceller may compute a mask to distinguish between target microphone audio signals that are echo-signal dominant and near-end speech dominant. The echo canceller may use the mask to adaptively update the transfer function or to modify the playback reference signal used by the transfer function to estimate the echo signals of the playback content.

Growing community of inventors

Los Angeles, CA, United States of America

Ante Jukic