A review of recent advances in visual speech decoding

作者：

Highlights：

• A detailed review of the recent advances in the area of visual speech decoding.

• Visual features tackling speaker dependency, head poses and temporal information.

• Dynamic audio-visual speech information fusion.

• Recent techniques of facial landmark localization.

• Summary of audio-visual speech databases and ASR performance on them.

摘要

•A detailed review of the recent advances in the area of visual speech decoding.•Visual features tackling speaker dependency, head poses and temporal information.•Dynamic audio-visual speech information fusion.•Recent techniques of facial landmark localization.•Summary of audio-visual speech databases and ASR performance on them.

论文关键词：Visual speech decoding,Automatic speech recognition,Lip-reading,Audio-visual speech recognition,Review

论文评审过程：Received 4 February 2014, Revised 16 May 2014, Accepted 26 June 2014, Available online 3 July 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.06.004