ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Combining evidence from a generative and a discriminative model in phoneme recognition

Joel Pinto, Hynek Hermansky

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. Multistream 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.


doi: 10.21437/Interspeech.2008-132

Cite as: Pinto, J., Hermansky, H. (2008) Combining evidence from a generative and a discriminative model in phoneme recognition. Proc. Interspeech 2008, 2414-2417, doi: 10.21437/Interspeech.2008-132

@inproceedings{pinto08_interspeech,
  author={Joel Pinto and Hynek Hermansky},
  title={{Combining evidence from a generative and a discriminative model in phoneme recognition}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={2414--2417},
  doi={10.21437/Interspeech.2008-132}
}