Discriminative training of HMM stream exponents for audio-visual speech recognition
- 27 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 3733-3736
- https://doi.org/10.1109/icassp.1998.679695
Abstract
We propose the use of discriminativetrainingbymeansofthe generalized probabilistic descent #GPD# algorithm to estimatehidden Markov model #HMM# stream exponents foraudio-visual speech recognition. Synchronized audio and visualfeatures are used to respectively train audio-only andvisual-only single-stream HMMs of identical topology bymaximum likelihood. A two-stream HMM is then obtainedby combining the two single-stream HMMs and introducingexponents that weigh the log-likelihood of each ...Keywords
This publication has 4 references indexed in Scilit:
- Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Maximum likelihood weighting of dynamic speech features for CDHMM speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- On the Integration of Auditory and Visual Parameters in an HMM-based ASRPublished by Springer Nature ,1996
- A MINIMUM ERROR RATE PATTERN RECOGNITION APPROACH TO SPEECH RECOGNITIONInternational Journal of Pattern Recognition and Artificial Intelligence, 1994