Keyword : Deep Bottleneck Feature


Investigation of DNN-Based Audio-Visual Speech Recognition
Satoshi TAMURA Hiroshi NINOMIYA Norihide KITAOKA Shin OSUGA Yurie IRIBE Kazuya TAKEDA Satoru HAYAMIZU 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10 ; pp. 2444-2451
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Acoustic modeling
Keyword: 
audio-visual speech recognitiondeep neural networkDeep Bottleneck Featuremulti-stream HMM
 Summary | Full Text:PDF(807.1KB)