Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition
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.
- URL: http://publications.idiap.ch/downloads/papers/2008/pinto-IS-2008.pdf
- Related documents: http://publications.idiap.ch/index.php/publications/showcite/pinto:rr08-20
Record created on 2010-02-11, modified on 2016-08-08