CONF
pinto:IS:2008/IDIAP
Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition
Pinto, Joel Praveen
Hermansky, Hynek
EXTERNAL
https://publications.idiap.ch/attachments/papers/2008/pinto-IS-2008.pdf
PUBLIC
https://publications.idiap.ch/index.php/publications/showcite/pinto:rr08-20
Related documents
Proceedings of Interspeech
2008
IDIAP-RR 08-20
We investigate the use of the log-likelihood of the features obtained from a generative Gaussian mixture model, and the posterior probability of phonemes from a discriminative multilayered perceptron in multi-stream combination for recognition of phonemes. Multi-stream combination techniques, namely early integration and late integration are used to combine the evidence from these models. By using multi-stream combination, we obtain a phoneme recognition accuracy of 74\% on the standard TIMIT database, an absolute improvement of 2.5\% over the single best stream.
REPORT
pinto:rr08-20/IDIAP
Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition
Pinto, Joel Praveen
Hermansky, Hynek
EXTERNAL
https://publications.idiap.ch/attachments/reports/2008/pinto-idiap-rr-08-20.pdf
PUBLIC
Idiap-RR-20-2008
2008
IDIAP
Submitted for publication
We investigate the use of the log-likelihood of the features obtained from a generative Gaussian mixture model, and the posterior probability of phonemes from a discriminative multilayered perceptron in multi-stream combination for recognition of phonemes. Multi-stream combination techniques, namely early integration and late integration are used to combine the evidence from these models. By using multi-stream combination, we obtain a phoneme recognition accuracy of 74\% on the standard TIMIT database, an absolute improvement of 2.5\% over the single best stream.