91
Voted
NAACL
2007
15 years 10 days ago
2007
This paper presents a way to perform speaker adaptation for automatic speech recognition using the stream weights in a multi-stream setup, which included acoustic models for “Ar...
96
Voted
ICMCS
2005
IEEE
15 years 4 months ago
2005
IEEE
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...