120 search results - page 17 / 24 » Maximum entropy models for speech confidence estimation |
SPEECH
2008
13 years 7 months ago
2008
In this paper, we describe a statistical approach to both an articulatory-to-acoustic mapping and an acoustic-to-articulatory inversion mapping without using phonetic information....
NIPS
1998
13 years 9 months ago
1998
We introduce a novel framework for simultaneous structure and parameter learning in hidden-variable conditional probability models, based on an entropic prior and a solution for i...
3DPVT
2004
IEEE
13 years 11 months ago
2004
IEEE
This paper describes methods for segmenting planar surfaces from noisy 3D data obtained from correlation stereo vision. We make use of local planar surface elements called patchle...
ICASSP
2010
IEEE
13 years 8 months ago
2010
IEEE
Voice conversion can be reduced to a problem to find a transformation function between the corresponding speech sequences of two speakers. Perhaps the most voice conversions meth...
ICMCS
2005
IEEE
14 years 1 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...