376 search results - page 11 / 76 » Analysis-by-synthesis features for speech recognition |
ICMCS
2005
IEEE
14 years 3 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...
ICCV
2005
IEEE
14 years 3 months ago
2005
IEEE
We present an approach to detecting and recognizing spoken isolated phrases based solely on visual input. We adopt an architecture that first employs discriminative detection of ...
ISCAS
2008
IEEE
14 years 4 months ago
2008
IEEE
Abstract— Especially for tasks like automatic meeting transcription, it would be useful to automatically recognize speech also while multiple speakers are talking simultaneously....
ICASSP
2010
IEEE
13 years 9 months ago
2010
IEEE
Random projection has been suggested as a means of dimensionality reduction, where the original data are projected onto a subspace using a random matrix. It represents a computati...
ICASSP
2011
IEEE
13 years 1 months ago
2011
IEEE
In current speech recognition systems mainly Short-Time Fourier Transform based features like MFCC are applied. Dropping the short-time stationarity assumption of the voiced speec...