SPEAKER NORMALIZATION AND PRONUNCIATION VARIANT MODELING: HELPFUL METHODS FOR IMPROVING RECOGNITION OF FAST SPEECH

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 299-302

  Pfau, Thilo ^a   Faltlhauser, Robert ^a   Ruske, Günther ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; SPEECH COMMUNICATION;

HIDDEN-MARKOV MODELS; MAXIMUM A POSTERIORI; MAXIMUM-LIKELIHOOD; MODEL VARIATION; PARAMETERS ESTIMATION; PRONUNCIATION VARIANTS; ROBUST PARAMETER ESTIMATION; SPEAKER NORMALIZATION; VARIANT MODELS; VOCAL-TRACT LENGTH NORMALIZATIONS;

HIDDEN MARKOV MODELS;

EID: 0011522737     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Morgan N., Fosler E., Mirghafori N., Speech Recognition Using On-line Estimation of Speaking Rate, Proc. Eurospeech '97, pp. 2079-2082, Rhodes, Greece, September 1997.
2. Mirghafori N., Fosler E., Morgan N., Towards Robustness to Fast Speech in ASR, Proc. ICASSP '96, Vol.1, pp. 335-338, Atlanta, Georgia, May 1996.
3. Mirghafori N., Fosler E., Morgan N., Fast Speakers in Large Vocabulary Continuous Speech Recognition: Analysis & Antidotes, Proc. Eurospeech '95, pp. 491-494, Madrid, Spain, September 1995.
4. Siegler M.A., Stern R.M., On the Effects of Speech Rate in Large Vocabulary Speech Recognition Systems, Proc. ICASSP '95, pp. 612-615, Detroit, Michigan, May 1995.
5. Pfau T., Ruske G., Creating Hidden Markov Models for Fast Speech, Proc. ICSLP '98, paper no. 255, Sydney, Australia, November/December 1998.
6. Pfau T., Ruske G., Estimating the Speaking Rate by Vowel Detection, Proc. ICASSP '98, pp. 945-948, Seattle, Washington, May 1998.
7. Takahashi J., Sagayama S., Vector-Field-Smoothed Bayesian Learning for Incremental Speaker Adaptation, Proc. ICASSP '95, pp. 696-699, Detroit, Michigan, May 1995.
8. Takahashi S., Sagayama S., Tied-Structure HMM Based on Parameter Correlation for Efficient Model Training, Proc. ICASSP '96, pp. 467-470, Atlanta, Georgia, May 1996.
9. Lee C.-H., Gauvain J.-L., Speaker Adaptation Based on MAP Estimation of HMM Parameters, Proc. ICASSP '93, pp. 558-561, Minneapolis, Minnesota, April 1993.
10. Eide E., Gish H., A Parametric Approach to Vocal Tract Length Normalization, Proc. ICASSP '96, pp. 346-348, Atlanta, Georgia, May 1996.
11. Zhan P., Westphal M., Speaker Normalization Based on Frequency Warping, Proc. ICASSP'97, pp. 1039-1042, Munich, Germany, April 1997.
12. Lee L., Rose R.C., Speaker Normalization Using Efficient Frequency Warping Procedures, Proc. ICASSP '96, pp. 353-356, Atlanta, Georgia, May 1996.
13. Westphal M., Schultz T., Waibel A., Linear Discriminant - A New Criterion For Speaker Normalization, Proc. ICSLP'98, paper no. 755, Sydney, Australia, November/December 1998.
14. Schiel F., Kipp A., Tillmann H.G., Statistical Modeling of Pronunciation: it's not the Model, it's the Data, Proc. Modeling Pronunciation Variation for Automatic Speech Recognition, pp.131-136, Rolduc, the Netherlands, May 1998.
15. Finke M., Waibel A., Speaking Mode Dependent Pronunciation Modeling in Large Vocabulary Conversational Speech Recognition, Proc. Eurospeech '97, pp. 2379-2382, Rhodes, Greece, September 1997.
16. Sloboda T., Dictionary Learning: Performance through Consistency, Proc. ICASSP '95, pp. 453-456, Detroit, Michigan, May 1995.