Modulation Wiener filter for improving speech intelligibility

Chung Chien Hsu, Kah Meng Cheong, Jen-Tzung Chien, Tai-Shih Chi

研究成果: Conference contribution同行評審

11 引文 斯高帕斯(Scopus)

摘要

This paper presents a single-channel high-dimensionalWiener filter in the spectro-temporal modulation domain. Unlike other conventional noise reduction techniques, the proposed algorithm not only reduces noise but also enhances the 'textures' of the speech signal. A non-iterative decision-directed noise estimation method is adopted to estimate the modulation SNR for the modulation-domain Wiener filter. The efficacy of the proposed algorithm in enhancing speech intelligibility is assessed using the short-time objective intelligibility (STOI) measure. Statistical analysis results demonstrate that our proposed algorithm can improve STOI scores in speech-shape noise (SSN) and white noise conditions, but not in babble noise condition, while the conventional Wiener filter fails to improve STOI scores in all three noise conditions.

原文English
主出版物標題2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面370-374
頁數5
ISBN(電子)9781467369978
DOIs
出版狀態Published - 4 8月 2015
事件40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, 澳大利亞
持續時間: 19 4月 201424 4月 2014

出版系列

名字ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2015-August
ISSN(列印)1520-6149

Conference

Conference40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
國家/地區澳大利亞
城市Brisbane
期間19/04/1424/04/14

指紋

深入研究「Modulation Wiener filter for improving speech intelligibility」主題。共同形成了獨特的指紋。

引用此