Tencent America LLC

Yong Xu

Meng Yu

Dong Yu

Shi-Xiong Zhang

Chunlei Zhang

Shi-xiong Zhang

Chao Weng

Jianming Liu

A method, computer program, and computer system is provided for automated speech recognition. Audio data corresponding to one or more speakers is received. Covariance matrices of target speech and noise associated with the received audio data are estimated based on a gated recurrent unit-based network. A predicted target waveform corresponding to a target speaker from among the one or more speakers is generated by a minimum variance distortionless response function based on the estimated covariance matrices.

All deep learning minimum variance distortionless response beamformer for speech separation and enhancement

A method of acoustic echo suppression using a recurrent neural network, performed by at least one processor, is provided. The method includes receiving a microphone signal and a far-end reference signal, estimating an echo suppressed signal and an echo signal based on the microphone signal and the far-end reference signal, estimating enhancement filters for the microphone signal based on the echo suppressed signal and the echo signal, generating an enhanced signal based on the enhancement filters, and adjusting the enhanced signal using automatic gain control (AGC) and outputting the adjusted signal.

Neuralecho: a self-attentive recurrent neural network for unified acoustic echo suppression, speaker aware speech enhancement and automatic gain control

There is included a method and apparatus comprising computer code for generating enhanced target speech from audio data, performed by a computing device, the method comprising: receiving audio data corresponding to one or more speakers; generating estimated an target speech, an estimated noise, and an estimated echo simultaneously based on the audio data using a jointly trained complex ratio mask; predicting frame-level multi-tap time-frequency (T-F) spatio-temporal-echo filter weights based on the estimated target speech, the estimated noise, and the estimated echo using a trained neural network model; and predicting enhanced target speech based on the frame-level multi-tap T-F spatio-temporal-echo filter weights.

ADL-UFE: all deep learning unified front-end system

Techniques for unified acoustic echo suppression using a recurrent neural network

A method, computer program, and computer system for separating a target voice from among a plurality of speakers is provided. Video data associated with the plurality of speakers and audio data associated with each of the one or more speakers are received. Video feature data is extracted from the received video data. The target voice is identified from among the plurality of speakers based on the received audio data and the extracted video feature data.

Multi-modal framework for multi-channel target speech separation

A method, computer system, and computer readable medium are provided for automatic speech recognition. Video data and audio data corresponding to one or more speakers is received. A minimum variance distortionless response function is applied to the received audio and video data. A predicted target waveform corresponding to a target speaker from among the one or more speakers is generated based on back-propagating the output of the applied minimum variance distortionless response function.

Growing community of inventors

Bellevue, WA, United States of America

Yong Xu