Apple Inc.

Mehrez Souden

Joshua D Atkins

Ante Jukic

Symeon Delikaris Manias

Jason Wung

Ramin Pishehvar

John Woodruff

Jonathan J Huang

Carlos M Avendano

Jonathan D Sheaffer

Matthew S Connolly

Peter A Raffensperger

Sabine Webel

Ronald J Guglielmone, Jr

Feipeng Li

Andreas Koutrouvelis

Martin E Johnson

Sean Anthony Ramprashad

Juha O Merimaa

Yoon Kim

Ashrith Deshpande

John Bridle

Symeon Delikaris-Manias

Feiping Li

Processing of ambience and speech can include extracting from audio signals, ambience and speech signals. One or more spatial parameters can be generated that define spatial characteristics of ambience sound in the one or more ambience audio signals. The primary speech signal, the one or more ambience audio signals, and the spatial parameters can be encoded into one or more encoded data streams. Other aspects are described and claimed.

Separating and rendering voice and ambience signals by offsetting impact of device movements

Implementations of the subject technology provide systems and methods for providing audio source separation for audio input, such as for audio devices having limited power and/or computing resources. The subject technology may allow an audio device to leverage processing and/or power resources of a companion device that is communicatively coupled to the audio device. The companion device may identify a noise condition of the audio device, select a source separation model based on the noise condition, and provide the source separation model to the audio device. In this way, the audio device can provide audio source separation functionality using a relatively small footprint source separation model that is specific to the noise condition in which the audio device is operated.

Audio source separation for audio devices

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

Systems and processes for operating an intelligent automated assistant are provided. In accordance with one example, a method includes, at an electronic device with one or more processors, memory, and a plurality of microphones, sampling, at each of the plurality of microphones of the electronic device, an audio signal to obtain a plurality of audio signals; processing the plurality of audio signals to obtain a plurality of audio streams; and determining, based on the plurality of audio streams, whether any of the plurality of audio signals corresponds to a spoken trigger. The method further includes, in accordance with a determination that the plurality of audio signals corresponds to the spoken trigger, initiating a session of the digital assistant; and in accordance with a determination that the plurality of audio signals does not correspond to the spoken trigger, foregoing initiating a session of the digital assistant.

Detecting a trigger of a digital assistant

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 device for reproducing spatial audio using a machine learning model may include at least one processor configured to receive multiple audio signals corresponding to a sound scene captured by respective microphones of a device. The at least one processor may be further 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 a target rendering configuration. The at least one processor may be further configured to provide, responsive to providing the multiple audio signals to the machine learning model, multichannel audio signals that comprise a spatial reproduction of the sound scene in accordance with the target rendering configuration.

Time domain neural networks for spatial audio reproduction

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

Processing input audio channels for generating spatial audio can include receiving a plurality of microphone signals that capture a sound field. Each microphone signal can be transformed into a frequency domain signal. From each frequency domain signal, a direct component and a diffuse component can be extracted. The direct component can be processed with a parametric renderer. The diffuse component can be processed with a linear renderer. The components can be combined, resulting in a spatial audio output. The levels of the components can be adjusted to match a direct to diffuse ratio (DDR) of the output with the DDR of the captured sound field. Other aspects are also described and claimed.

Growing community of inventors

Los Angeles, CA, United States of America

Mehrez Souden