Audio-visual speech enhancement using hierarchical extreme learning machine

Tassadaq Hussain, Yu Tsao, Hsin Min Wang, Jia Ching Wang, Sabato Marco Siniscalchi, Wen Hung Liao

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

Recently, the hierarchical extreme learning machine (HELM) model has been utilized for speech enhancement (SE) and demonstrated promising performance, especially when the amount of training data is limited and the system does not support heavy computations. Based on the success of audio-only-based systems, termed AHELM, we propose a novel audio-visual HELM-based SE system, termed AVHELM that integrates the audio and visual information to confrontate the unseen non-stationery noise problem at low SNR levels to attain improved SE performance. The experimental results demonstrate that AVHELM can yield satisfactory enhancement performance with a limited amount of training data and outperforms AHELM in terms of three standardized objective measures under matched and mismatched testing conditions, confirming the effectiveness of incorporating visual information into the HELM-based SE system.

原文???core.languages.en_GB???
主出版物標題EUSIPCO 2019 - 27th European Signal Processing Conference
發行者European Signal Processing Conference, EUSIPCO
ISBN(電子)9789082797039
DOIs
出版狀態已出版 - 9月 2019
事件27th European Signal Processing Conference, EUSIPCO 2019 - A Coruna, Spain
持續時間: 2 9月 20196 9月 2019

出版系列

名字European Signal Processing Conference
2019-September
ISSN(列印)2219-5491

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???27th European Signal Processing Conference, EUSIPCO 2019
國家/地區Spain
城市A Coruna
期間2/09/196/09/19

指紋

深入研究「Audio-visual speech enhancement using hierarchical extreme learning machine」主題。共同形成了獨特的指紋。

引用此