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

Robert Wielgat; Tomasz P. Zielinski; Pawel Swietojanski; Piotr Zoladz; Daniel Król; Tomasz Wozniak; Stanislaw Grabias

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

Robert Wielgat, Tomasz P. Zielinski, Pawel Swietojanski, Piotr Zoladz, Daniel Król, Tomasz Wozniak, Stanislaw Grabias

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

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.

Original language	English
Title of host publication	INTERSPEECH 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007
Publisher	ISCA
Pages	1705-1708
Number of pages	4
Publication status	Published - 2007
Event	8th Annual Conference of the International Speech Communication Association - Antwerp, Belgium Duration: 27 Aug 2007 → 31 Aug 2007

Conference

Conference	8th Annual Conference of the International Speech Communication Association
Country/Territory	Belgium
City	Antwerp
Period	27/08/07 → 31/08/07

Access to Document

Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciationFinal published version, 149 KB

http://www.isca-speech.org/archive/interspeech_2007/i07_1705.html

Cite this

Wielgat, R., Zielinski, T. P., Swietojanski, P., Zoladz, P., Król, D., Wozniak, T., & Grabias, S. (2007). Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation. In INTERSPEECH 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007 (pp. 1705-1708). ISCA. http://www.isca-speech.org/archive/interspeech_2007/i07_1705.html

@inproceedings{8e754fbbc13b4424b77b6612f455b14c,

title = "Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation",

abstract = "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.",

author = "Robert Wielgat and Zielinski, {Tomasz P.} and Pawel Swietojanski and Piotr Zoladz and Daniel Kr{\'o}l and Tomasz Wozniak and Stanislaw Grabias",

year = "2007",

language = "English",

pages = "1705--1708",

booktitle = "INTERSPEECH 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007",

publisher = "ISCA",

note = "8th Annual Conference of the International Speech Communication Association ; Conference date: 27-08-2007 Through 31-08-2007",

}

Wielgat, R, Zielinski, TP, Swietojanski, P, Zoladz, P, Król, D, Wozniak, T & Grabias, S 2007, Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation. in INTERSPEECH 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007. ISCA, pp. 1705-1708, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, 27/08/07. <http://www.isca-speech.org/archive/interspeech_2007/i07_1705.html>

Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation. / Wielgat, Robert; Zielinski, Tomasz P.; Swietojanski, Pawel et al.
INTERSPEECH 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007. ISCA, 2007. p. 1705-1708.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Comparison of HMM and DTW methods in automatic recognition of pathological phoneme pronunciation

AU - Wielgat, Robert

AU - Zielinski, Tomasz P.

AU - Swietojanski, Pawel

AU - Zoladz, Piotr

AU - Król, Daniel

AU - Wozniak, Tomasz

AU - Grabias, Stanislaw

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

M3 - Conference contribution

SP - 1705

EP - 1708

BT - INTERSPEECH 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007

PB - ISCA

T2 - 8th Annual Conference of the International Speech Communication Association

Y2 - 27 August 2007 through 31 August 2007

ER -

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

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this