Research on Robust Audio-Visual Speech Recognition Algorithms

Automatic speech recognition (ASR) that relies on audio input suffers from significant degradation in noisy conditions and is particularly vulnerable to speech interference. However, video recordings of speech capture both visual and audio signals, providing a potent source of information for traini...

詳細記述

書誌詳細

出版年:	Mathematics
主要な著者:	Wenfeng Yang, Pengyi Li, Wei Yang, Yuxing Liu, Yulong He, Ovanes Petrosian, Aleksandr Davydenko
フォーマット:	論文
言語:	英語
出版事項:	MDPI AG 2023-04-01
主題:	multi-model deep learning speech recognition lip reading audiovisual speech recognition model comparison MOCO
オンライン･アクセス:	https://www.mdpi.com/2227-7390/11/7/1733