Agora Lab, Inc.

Jimeng Zheng

Bo Wu

Song Li

Jianyuan Feng

Ruofei Chen

Xiaohan Zhao

Liangliang Wang

A real-time communication software application for generating spatial audio with uniform reverberation in a real-time communication session is performed by an electronic communication device. The application is adapted to remove the reverberation of recorded speech signals from far-end participants by the dereverberation approach, render the direct sound parts by filtering the output signals by head-related transfer functions of desired directions, generate reverberant sound parts by convolving the output signals from with uniform room impulse responses or an artificial reverberator, and combine direct and reverberant sound components to generate spatialized speech signals. When speakers and listeners are located in two virtual conference rooms, the reverberation of the two rooms are coupled. The reverberant sound parts are then generated by convolving the output signals and coupled RIRs from the two rooms.

System for generating spatial audio with uniform reverberation in real-time communication

A computer-implemented method for suppressing noise from audio signal uses both statistical noise estimation and neural network noise estimation to achieve more desirable noise reduction. The method is performed by a noise suppression computer software application running on an electronic device. The noise suppression computer software application first transforms the speech signal in time domain into frequency domain before determining a statistical noise estimate and a neural network noise estimate. The noise suppression computer software application merges the two noise estimates to derive a final noise estimate, and determines and refines a noise suppression filter. The filter is applied to the speech signal in frequency domain to obtain an enhanced signal. The enhanced signal is transformed back into time domain.

System and method for suppressing noise from audio signal

A computer-implemented method for generating spatial audio with uniform reverberation in a real-time communication session is performed by a real-time communication software application running on an electronic communication device. The method includes removing the reverberation of recorded speech signals from far-end participants by the dereverberation approach, rendering the direct sound parts by filtering the output signals by head-related transfer functions of desired directions, generating reverberant sound parts by convolving the output signals from with uniform room impulse responses or an artificial reverberator, combining direct and reverberant sound components to generate spatialized speech signals. When speakers and listeners are located in two virtual conference rooms, the reverberation of the two rooms are coupled. The reverberant sound parts are then generated by convolving the output signals and coupled RIRs from the two rooms.

Growing community of inventors

Shanghai, China

Jimeng Zheng