Loading...
report
Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition
2008
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.
Loading...
Name
pinto-idiap-rr-08-20.pdf
Access type
openaccess
Size
109.16 KB
Format
Adobe PDF
Checksum (MD5)
8ce4dfaa71bd369ff189a374d908acb6