Agora Lab, Inc.

Ruofei Chen

Siqiang Yao

Shie Qian

Xiaohan Zhao

Zehua Gao

Bo Wu

Fan Li

Yi Hang Lv

Jimeng Zheng

Yunyun Ji

Zihe Liu

Liangliang Wang

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 method for encoding multiple descriptions for a media stream includes: determining, for a current block of the media stream, a first number of duplicate blocks, determining, for the current block, a plurality of complementary forward gain factors, and determining a first number of descriptions for the current block by applying the plurality of complementary forward gain factors to the first number of duplicate blocks. A method for decoding multiple descriptions for a media stream includes: determining, for a current block of the media stream, a first number of descriptions from the media stream, in which each description comprises a scaled block corresponding to the current block, determining backward gain factors for the first number of scaled blocks, and determining the current block by applying the backward gain factors to the first number of scaled blocks.

Gain control for multiple description coding

A new audio quality assessment system includes an assessment system running in a receiver system of a VoIP communication system. The new audio quality assessment system determines an accurate MOS of a VoIP call within a time window. The audio quality assessment system determines an effective PLC counter, a PLC impact factor, an effective AS counter, an AS impact factor, a network impact factor, a codec type of the received voice packets, a bitrate of the received voice packets, an initial MOS from a configured codec-bitrate MOS table, and determines the accurate MOS based on these data. The determined MOS is more accurate and efficiently obtained since it is based on efficiently collected statistics of the receiver system's modules and a pre-configured codec-bitrate MOS table.

Voice quality assessment system

A method includes extracting, from a frame of the audio sample, spectral features indicative of cochlear impulse response of an auditory system; obtaining an estimate of a speech signal in the frame from a neural network that is trained, during a training phase, to accept the spectral features as input and output the estimate of the speech signal, where the estimate of the speech signal includes reverberation and excludes noise present in the frame; mapping the estimate of the speech signal to a frequency domain of the frame using mapping parameters obtained during the training phase to obtain an estimate of a reverberant speech spectrum in the frame; and obtaining, from a time-distributed neural network, a dereverberant frame of the frame, where the estimate of the reverberant speech spectrum in the frame is used as an input to the time-distributed neural network.

Simultaneous dereverberation and denoising via low latency deep learning

A method for decoding multiple descriptions for a media stream includes decoding at least one of a first description and a second description from the media bitstream, wherein the first description and the second description are associated with a current sample of the media bitstream and independently decodable; based on a determination that the second description is missing, reconstructing, by a decoder, the current sample by performing a third shifting operation on the first description, wherein the third shifting operation on the first description comprises left shifting the first description by one bit; and based on a determination that both the first description and the second description have been received, reconstructing, by the decoder, the current sample by summing the first description and the second description. An encoding method is also provided.

Growing community of inventors

Shanghai, China

Ruofei Chen