ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

On acquiring speech production knowledge from articulatory measurements for phoneme recognition

D. Neiberg, G. Ananthakrishnan, Mats Blomberg

The paper proposes a general version of a coupled Hidden Markov/Bayesian Network model for performing phoneme recognition on acoustic-articulatory data. The model uses knowledge learned from the articulatory measurements, available for training, for phoneme recognition on the acoustic input. After training on the articulatory data, the model is able to predict 71.5% of the articulatory state sequences using the acoustic input. Using optimized parameters, the proposed method shows a slight improvement for two speakers over the baseline phoneme recognition system which does not use articulatory knowledge. However, the improvement is only statistically significant for one of the speakers. While there is an improvement in recognition accuracy for the vowels, diphthongs and to some extent the semi-vowels, there is a decrease in accuracy for the remaining phonemes.


doi: 10.21437/Interspeech.2009-428

Cite as: Neiberg, D., Ananthakrishnan, G., Blomberg, M. (2009) On acquiring speech production knowledge from articulatory measurements for phoneme recognition. Proc. Interspeech 2009, 1387-1390, doi: 10.21437/Interspeech.2009-428

@inproceedings{neiberg09_interspeech,
  author={D. Neiberg and G. Ananthakrishnan and Mats Blomberg},
  title={{On acquiring speech production knowledge from articulatory measurements for phoneme recognition}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1387--1390},
  doi={10.21437/Interspeech.2009-428}
}