Kai Li is a master student in (Department of Computer Science and Technology, Tsinghua University), supervised by Prof. Xiaolin Hu. And then he will complete his master's career in Hu Lab from 2021 to 2024. He was an intern at Tencent AI Lab, mainly doing research on causal speech separation, supervi He got his bachelor's degree from Department of Computer Technology and Application, the Qinghai University, supervised by Prof. Jianqiang Huang and Prof. Chunmei Li in 2020. His research interests include computer vision, deep learning, speech separation and cross-model speech separation. |
![]() |
![]() |
Open source audio-visual dataset processing script.
[
Github
] MoreFollowing are the steps to generate training and testing data. There are several parameters to change in order to match different purpose. |
![]() |
Dual-path RNN
[
Github
] [
知乎:
DPRNN阅读笔记] MoreEfficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch. |
![]() |
Audio-visual speech separation method :-)
[
Github
] [
知乎:
LLCP阅读笔记] MoreThe project is an audiovisual model reproduced by the contents of the paper Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation. |
![]() |
Calculatie Audio‘s SNR and SDR.
[
GitHub
] |
![]() |
A must-read paper and tutorial list for speech separation based on neural networks
[
Github
] MoreNone |
![]() |
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement
[
GitHub ] [
知乎:
Conv-TasNet阅读笔记] |
![]() |
According to funcwj's uPIT, the training code supporting multi-gpu is written, and the Dataloader is reconstructed.
[
Github
] [
知乎:
uPIT阅读笔记] MoreNone |
![]() |
Deep clustering in the field of speech separation implemented by pytorch
[
GitHub
] [
知乎:
DPCL阅读笔记] |
![]() |
Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
[
GitHub
] |
(* equal contribution, # corresponding author)