ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

K-NN versus Gaussian in HMM-based recognition system

Claude Montacié, Marie-José Caraty, Fabrice Lefèvre

For many years, the K-Nearest Neighbours method (K-NN) is known as one of the best probability density function (pdf) estimator. A fast K-NN algorithm has been developed and tested on the TIMIT database with a gain in computational time of 99;8%. The K-NN decision principle has been assessed on a frame by frame phonetic identification. A method to integrate K-NN estimator pdf in a HMM-based system is proposed and tested on an acoustic-phonetic decoding task. Finally, preliminary experiments are performed on the HMM topology inference.


doi: 10.21437/Eurospeech.1997-175

Cite as: Montacié, C., Caraty, M.-J., Lefèvre, F. (1997) K-NN versus Gaussian in HMM-based recognition system. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 529-532, doi: 10.21437/Eurospeech.1997-175

@inproceedings{montacie97_eurospeech,
  author={Claude Montacié and Marie-José Caraty and Fabrice Lefèvre},
  title={{K-NN versus Gaussian in HMM-based recognition system}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={529--532},
  doi={10.21437/Eurospeech.1997-175},
  issn={1018-4074}
}