Agora Lab, Inc.

Siqiang Yao

Ruofei Chen

Shie Qian

Zehua Gao

Xiaohan Zhao

Fan Li

Yi Hang Lv

Yunyun Ji

Zihe Liu

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

Siqiang Yao