TOP-DOWN BOTTOM-UP HYBRID CLUSTERING ALGORITHM FOR ACOUSTIC-PHONETIC MODELING OF SPEECH

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

Volumn , Issue , 1999, Pages 1343-1346

  Mariño, José B ^a   Nogueiras, Albino ^a  

^a UNIVERSITAT POLITÈCNICA DE CATALUNYA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODELING; HIDDEN MARKOV MODELS; LINGUISTICS; SPEECH COMMUNICATION; SPEECH RECOGNITION;

ACOUSTICS MODEL; BOTTOM UP; CLUSTERING TECHNIQUES; HYBRID ALGORITHMS; HYBRID CLUSTERING ALGORITHM; OPTIMISATIONS; PHONETIC UNITS; RELEVANT TARGET; SPEECH RECOGNITION SYSTEMS; TOPDOWN;

CLUSTERING ALGORITHMS;

EID: 85009080774     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. J. B. Mariño, A. Nogueiras, A. Bonafonte, "The demiphone: an efficient subword unit for Continuous Speech Recognition", Proc. EUROSPEECH'97, pp. 1215-1218, Rhodes, Greece (September 1997).
2. J. B. Mariño, P. Pachès-Leal, A. Nogueiras, "The demiphone versus the triphone in a decision-tree state-tying framework", Proc. ICSLP'98, pp. 2463-2466, Sydney, Australia (November 1998).
3. K-F Lee, “Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition”, IEEE Trans. ASSP, vol. 38, nº4, pp. 599-609 (April 1990).
4. D. Gibbon, R. Moore, R. Winski (ed.), “Handbook of Standards and Resources for Spoken Language Systems”, Mouton de Gruyter, 1997.
5. M.-Y. Hwang, X. Huang, F. A. Alleva, “Predicting unseen triphones with senones”, IEEE Trans. SAP, vol. 4, nº6, pp. 412-419 (November 1996).
6. K-F Lee et al., “Allophone clustering for continuous speech recognition”, Proc. ICASSP'90, pp.749-752, Albuquerque, USA (April 1990).
7. A. Moreno, R. Winsky, “Spanish Fixed Network Speech Corpus”, SpeechDat Project LRE-63314.
8. A. Bonafonte and J.B. Mariño, “Language Modeling using X-grams", Proc. ICSLP96, pp. 394-397, Philadelphia, USA (October 1996).