The performance of automatic speech recognition (ASR) systems severely
d...
It has been shown that the intelligibility of noisy speech can be improv...
Speech restoration aims to remove distortions in speech signals. Prior
m...
Speech super-resolution (SR) is a task to increase speech sampling rate ...
This study addresses robust automatic speech recognition (ASR) by introd...
The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand
Ch...
With more deep learning techniques being introduced into the knowledge
t...
Deep neural networks are often coupled with traditional spatial filters,...
Deep neural networks (DNNs) have been successfully used for multichannel...
In this work, we propose a new model called triple-path attentive recurr...
Permutation-invariant training (PIT) is a dominant approach for addressi...
Speech restoration aims to remove distortions in speech signals. Prior
m...
This study investigates robust speaker localization for con-tinuous spee...
Deep neural networks (DNNs) represent the mainstream methodology for
sup...
On-device end-to-end speech recognition poses a high requirement on mode...
Music source separation is important for applications such as karaoke an...
We propose a dual-path self-attention recurrent neural network (DP-SARNN...
We propose speaker separation using speaker inventories and estimated sp...
We propose multi-microphone complex spectral mapping, a simple way of
ap...
Speech enhancement in the time domain is becoming increasingly popular i...
As an important technique for modeling the knowledge states of learners,...
This study proposes a multi-microphone complex spectral mapping approach...
In recent years, supervised approaches using deep neural networks (DNNs)...
We address talker-independent monaural speaker separation from the
persp...
Monaural speech enhancement has made dramatic advances since the introdu...
This study investigates phase reconstruction for deep learning based mon...
This paper proposes an end-to-end approach for single-channel
speaker-in...
Speech separation is the task of separating target speech from backgroun...
This paper proposed a class of novel Deep Recurrent Neural Networks whic...
This paper presented our work on applying Recurrent Deep Stacking Networ...