The experiments also show that the audio-visual continuous speech recognition system is robust in noisy environments.

基于特征口形的音频-视频混合连续语音识别系统具有很好的抗噪性。

youdao

Lip is one of the most important facial features, and plays key roles in a variety of fields such as audio-visual speech, authentication, lip synchronization, face recognition, etc.

嘴唇是人脸特征的重要组成部分，在音视频识别、认证、嘴唇同步、人脸识别等方面都很重要。

youdao

However, audio-recognition system only USES the audio information of speech, and ignores the visual features of it. Under the noise circumstance, the recognition rate declines so much.

但语音识别系统忽略语言的视觉特性，仅仅利用听觉特性，使得语音识别系统在噪声环境下，识别率大大下降。

youdao