Tencent America LLC

Tencent Technology (shenzhen) Company Limited

Shenzhen Bailu Outdoor Products Co., Ltd

Vulcan Inc.

Shenzhen Hightide Biopharmaceutical, Ltd.

Meng Yu

Dong Yu

Yong Xu

Shi-Xiong Zhang

Dan Su

Xincheng Jiang

Yi Gao

Min Luo

Chengzhu Yu

Heng Lu

Chunlei Zhang

Lianwu Chen

Shi-xiong Zhang

Ji Meng Zheng

Yu Wang

Yong Liu

Jie Chen

Keith David Rosema

Liping Liu

Chao Weng

Richard Earl Simpkinson

Jun Feng

Weiwei Li

Jimeng Zheng

Omer Rosenbaum

Rusty Allen Gerard

Yanmin Qian

Shamyl Emrich Zakariya

Xuan Ji

Wenbin Yang

Zhu Chen

Xinxiang Fu

Kai Xia

Hongyang Chen

Hao Zhang

Jianming Liu

David Joseph Martinez

Tyler Jay Perry

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 and apparatus comprising computer code configured to cause a processor or processors to receive an audio signal obtained from a microphone, input the audio signal into a neural-network based AEC model, and output an AEC signal from the neural-network based AEC model in which AEC is applied to the audio signal, and the AEC signal is a version of the audio signal in which acoustic echo noise of the audio signal is suppressed and target audio of the audio signal is sustained.

Kalmannet: a learnable Kalman filter for acoustic echo cancellation

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

An apparatus and a method include receiving an input audio signal to be processed by a multi-band synchronized neural vocoder. The input audio signal is separated into a plurality of frequency bands. A plurality of audio signals corresponding to the plurality of frequency bands is obtained. Each of the audio signals is downsampled, and processed by the multi-band synchronized neural vocoder. An audio output signal is generated.

Multi-band synchronized neural vocoder

A method, computer program, and computer system is provided for an all-deep-learning based AEC system by recurrent neural networks. The model consists of two stages, echo estimation stage and echo suppression stage, respectively. Two different schemes for echo estimation are presented herein: linear echo estimation by multi-tap filtering on far-end reference signal and non-linear echo estimation by single-tap masking on microphone signal. A microphone signal waveform and a far-end reference signal waveform are received. An echo signal waveform is estimated based on the microphone signal waveform and a far-end reference signal waveform. A near-end speech signal waveform is output based on subtracting the estimated echo signal waveform from the microphone signal waveform, and echoes are suppressed within the near-end speech signal waveform.

Neural-echo: an unified deep neural network model for acoustic echo cancellation and residual echo suppression

A method, computer system, and computer readable medium are provided for activating speech recognition based on keyword spotting (KWS). Waveform data corresponding to one or more speakers is received. One or more direction features are extracted from the received waveform data. One or more keywords are determined from the received waveform data based on the one or more extracted features. Speech recognition is activated based on detecting the determined keyword.

Multi-look enhancement modeling and application for keyword spotting

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 far-field pickup device including a device body and a microphone pickup unit is provided. The microphone pickup unit is configured to collect user speech and an echo of a first sound signal output by the device body, and transmit, to the device body, a signal obtained through digital conversion of the collected user speech and the echo. The device body includes a signal playback source, a synchronizing signal generator, a horn, a delay determining unit, and an echo cancellation unit configured to perform echo cancellation on the signal transmitted by the microphone pickup unit to obtain a collected human voice signal.

Far-field pickup device and method for collecting voice signal in far-field pickup device

Systems and techniques for enhancing the physical games with augmented reality is described. A system identifies a characteristic of a physical object that is located on a physical surface. The system obtains, based on the characteristic, information indicative of a rule set for the game and a state of the game based on the characteristic. A game engine is initialized based on the rule set and game state. The game engine generates a subsequent state for the game. The system renders, based on the subsequent state, an augmented reality display that incorporates the physical surface and physical object.

Physical games enhanced by augmented reality

This application discloses a sound acquisition component array, including: two first sound acquisition components, two second sound acquisition components, and two third sound acquisition components. The two second sound acquisition components are located at a first side of a line connecting the two first sound acquisition components, and the two third sound acquisition components are located at a second side of the connecting line that is opposite to the first side of the connecting line; the two second sound acquisition components are symmetrical about a perpendicular bisector of the connecting line, and the two third sound acquisition components are symmetrical about the perpendicular bisector; and a distance between the two first sound acquisition components, a distance between the two second sound acquisition components, and a distance between the two third sound acquisition components are respectively different from one another along a direction defined by the connecting line.

Sound acquisition component array and sound acquisition device

Unified deep neural network model for acoustic echo cancellation and residual echo suppression

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 multi-person speech separation method is provided for a terminal. The method includes extracting a hybrid speech feature from a hybrid speech signal requiring separation, N human voices being mixed in the hybrid speech signal, N being a positive integer greater than or equal to 2; extracting a masking coefficient of the hybrid speech feature by using a generative adversarial network (GAN) model, to obtain a masking matrix corresponding to the N human voices, wherein the GAN model comprises a generative network model and an adversarial network model; and performing a speech separation on the masking matrix corresponding to the N human voices and the hybrid speech signal by using the GAN model, and outputting N separated speech signals corresponding to the N human voices.

Multi-person speech separation method and apparatus using a generative adversarial network model

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.

Multi-tap minimum variance distortionless response beamformer with neural networks for target speech separation

Growing community of inventors

Bellevue, WA, United States of America

Meng Yu