huihuiwei Goto Github PK

acousticsourcemodeling

In line array systems, it is assumed that all sources are equal to guarantee a correct performance in the sound radiation of these, however, in practice this does not happen, since some components of the sources, which are characterized as Thiele Small parameters are rarely equal despite being of the same model, making the performance of a line arr

channel-decorrelation

multi-channel target speech extraction with channel decorrelation and target speaker adaptation

msr

多区声场再现

nn-inference-template

Neural network inference template for real-time cricital audio environments - presented at ADC23

partialspoof

public

acoustic toolbox to find, reconstruct or optimize sound sources with impedance boundary conditions

rir-generator

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

speaker_extraction_spex

multi-scale time domain speaker extraction

supdeq

SUpDEq - Spatial Upsampling by Directional Equalization

u-tasnet-beam

wase_202112

PyTorch implementation of WASE described in our ICASSP 2021: "Wase: Learning When to Attend for Speaker Extraction in Cocktail Party Environments"