Discriminatively trained features using fMPE for multi-stream audio-visual speech recognition

Jing Huang, Daniel Povey. Discriminatively trained features using fMPE for multi-stream audio-visual speech recognition. In INTERSPEECH 2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005. pages 777-780, ISCA, 2005. [doi]

Abstract

Abstract is missing.