An evaluation of using mutual information for selection of acoustic-features representation of phonemes for speech recognition

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 2129-2132

  Omar, Mohamed Kamal ^a   Chen, Ken ^a   Hasegawa Johnson, Mark ^a   Brandman, Yigal ^b  

^a University of Illinois at Urbana Champaign   (United States)

^b Phonetact Inc   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FACE RECOGNITION; INFORMATION USE; STEREOPHONIC BROADCASTING;

ACOUSTIC FEATURES; CORRELATION COEFFICIENT; KULLBACK-LIEBLER DIVERGENCES; MAXIMUM MUTUAL INFORMATION; MEL FREQUENCY CEPSTRUM COEFFICIENTS; MUTUAL INFORMATIONS; PHONEME RECOGNITION; SPEECH RECOGNITION SYSTEMS;

SPEECH RECOGNITION;

EID: 33947688163     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Katrin Kirchhoff, Gemot A. Fink, and Gerhard Sagerer, "Conversational Speech Recognition Using Acoustic And Ariculatory Input" IEEE Proceedings of ICASSP, Istanbul, 2000.
2. Daniel P. W. Ellis, Jeff A. Bilmes "Using Mutual Information To Design Feature Combinations" Int. Conf. on Spoken Language Processing, 2000, vol. 3, pp. 79-82.
3. Mark Hasegawa-Johnson "Time-Frequency Distribution of Partial Phonetic Information Measured using Mutual Information" Int. Conf. on Spoken Language Processing, Beijing, 2000, pp. 133-136.
4. Daphne Koller, Mehran Sahami "Toward Optimal Feature Selection" Proceedings of the 13th International Conference on Machine Learning (ML), Bari, Italy, July 1996, pp. 284-292.
5. M. Kamal Omar, Mark Hasegawa-Johnson "Maximum Mutual Information Based Acoustic-Features Representation of Phonlogical Features For Speech Recognition" IEEE Proceedings of ICASSP, Florida, 2002.
6. Mohamed Kamal Omar, "Phonetic Segmentation of Arabic Speech for Verification Using HMM", M. Sc. thesis, Cairo Univerity, Egypt, January 1999.