logo Idiap Research Institute        
 [BibTeX] [Marc21]
Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition
Type of publication: Idiap-RR
Citation: pinto:rr08-20
Number: Idiap-RR-20-2008
Year: 2008
Institution: IDIAP
Note: Submitted for publication
Abstract: 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.
Userfields: ipdmembership={speech},
Keywords:
Projects Idiap
Authors Pinto, Joel Praveen
Hermansky, Hynek
Crossref by pinto:IS:2008
Added by: [UNK]
Total mark: 0
Attachments
  • pinto-idiap-rr-08-20.pdf
  • pinto-idiap-rr-08-20.ps.gz
Notes