ISCA Archive Interspeech 2007
ISCA Archive Interspeech 2007

Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation

Robert Wielgat, Tomasz P. Zieliński, Paweł Świętojański, Piotr Żołądź, Daniel Król, Tomasz Woźniak, Stanisław Grabias

In the paper recently proposed Human Factor Cepstral Coefficients (HFCC) are used to automatic recognition of pathological phoneme pronunciation in speech of impaired children and efficiency of this approach is compared to application of the standard Mel-Frequency Cepstral Coefficients (MFCC) as a feature vector. Both dynamic time warping (DTW), working on whole words or embedded phoneme patterns, and hidden Markov models (HMM) are used as classifiers in the presented research. Obtained results demonstrate superiority of combining HFCC features and modified phoneme-based DTW classifier.


doi: 10.21437/Interspeech.2007-479

Cite as: Wielgat, R., Zieliński, T.P., Świętojański, P., Żołądź, P., Król, D., Woźniak, T., Grabias, S. (2007) Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation. Proc. Interspeech 2007, 1705-1708, doi: 10.21437/Interspeech.2007-479

@inproceedings{wielgat07_interspeech,
  author={Robert Wielgat and Tomasz P. Zieliński and Paweł Świętojański and Piotr Żołądź and Daniel Król and Tomasz Woźniak and Stanisław Grabias},
  title={{Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation}},
  year=2007,
  booktitle={Proc. Interspeech 2007},
  pages={1705--1708},
  doi={10.21437/Interspeech.2007-479}
}