@inproceedings{a65c91a6294445e3a2e60756d2d9bc02,
title = "A Dual-Channel Three-Stage Model for DoA and Speech Enhancement",
abstract = "During the pandemic, teleconferencing becomes a necessity to our daily lives. It drives the demand for an integrated system which is not only able to effectively enhance speech sounds, but also to localize the speaker for video enhancement. In this paper, we propose a neural network based composite system which integrates a DoA estimator and a neural beamformer for dual-channel speech enhancement. The proposed system can accomplish two tasks at the same time by using sound signals received from dual microphones. The estimated DoA is converted into a spatial angle related feature, which provides complementary information to boost performance of the neural beamformer. The proposed system is evaluated in simulated far-field conditions with reverberations and noise. Simulation results demonstrate the proposed system outperforms stand-alone baseline systems in either one of the two tasks and achieves comparable results to the best stand-alone models in either one of the two tasks.",
author = "Wu, {Meng Hsuan} and Shen, {Yih Liang} and Chou, {Hsuan Cheng} and Shih, {Bo Wun} and Chi, {Tai Shih}",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 ; Conference date: 31-10-2023 Through 03-11-2023",
year = "2023",
doi = "10.1109/APSIPAASC58517.2023.10317282",
language = "English",
series = "2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1064--1068",
booktitle = "2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023",
address = "United States",
}