AIConfPaper
← Search

Zirun Zhu

2 accepted papers

2023

Real-Time Audio-Visual End-To-End Speech Enhancement

Zirun Zhu, Hemin Yang, Min Tang, Ziyi Yang, Sefik Emre Eskimez, Huaming Wang
ICASSP 2023accepted

Audio-visual speech enhancement (AV-SE) methods utilize auxiliary visual cues to enhance speakers’ voices. Therefore, technically they should be able to outperform the audio-only speech enhancement (SE) methods. However, there are few works in the literature on an AV-SE system that can work in real…

Cited by 0Source ↗Scholar ↗
2022

VarArray: Array-Geometry-Agnostic Continuous Speech Separation

Takuya Yoshioka, Xiaofei Wang, Dongmei Wang, Min Tang, Zirun Zhu, Zhuo Chen +1
ICASSP 2022accepted

Continuous speech separation using a microphone array was shown to be promising in dealing with the speech overlap problem in natural conversation transcription. This paper proposes VarArray, an array-geometry-agnostic speech separation neural network model. The proposed model is applicable to any n…

Cited by 0Source ↗Scholar ↗