A comparison of phoneme decision tree (PDT) and context adaptive phone (CAP) based approaches to vocabulary-independent speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 1994, Pages I541-I544

  Russell, M J ^a   Kowell, P ^a   Downey, S N ^a   Browning, S R ^a   Moore, R K ^a  

^a DRA   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

BINARY TREES; DECISION TREES; EQUIVALENCE CLASSES; SIGNAL PROCESSING; TELEPHONE SETS;

AUTOMATIC SPEECH RECOGNITION; BINARY DECISION TREES; CONTEXT INDEPENDENT; CONTEXT-SENSITIVE; DIRECT ANALYSIS; INDEPENDENT SPEECH; METHODOLOGICAL COMPARISON; TRAINING CORPUS;

SPEECH RECOGNITION;

EID: 3843133456     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1994.389237     Document Type: Conference Paper

References (14)

1. L R Bahl, P V de Souzal P S Gopalakrishnan, D Nahamoo, M A Picheny. "Decision Trees for Phonological Rules in Continuous Speech", Proc ICASSP'91, Toronto, 1991.
2. P Bamberg and L Gillick. "Phoneme-in-context. modelling for Dragon's continuous speech recoguiser". Proc. DARPA Speech and Natural Language Workshop, Hidden Valley, Pa, June 1990.
3. S Browning, J McQuillan. M Russell and Mromlinson, "Texts of material recorded in the SI89 speech corpus", SP4 Research Note No. 142, RSRE, February 1991.
4. Sue Browning, Martin Russell and Simon Downey, "Phoneme Decision Tree Constrnction for Automatic Speech Recognition", DRA Malvern memorandum 4666, March 1993.
5. L Deng, M Lennig, F Seitz and P Mermelstein, "Large vocabulary word recognition using context-dependent allophonic hidden Markov models", Computer Speech and Language, 4, pp 345-357, 1990.
6. Simon Downey, "Initial experiments with phoneme decision trees", DRA Malvern memora.ndum 4701, February 1993.
7. H-W Hon and K-F Lee. "On vocabularyindependent speech modelling". Proc. Int. Conf. on Acoustics, Speech and Signal Processing, pp 725-728, Albuquerque, NM. 3-6 April 1990.
8. K F Lee. "Large vocabulary speaker-independent continuous speech recognition: the SPHINX system". Ph.D. Thesis, Carnegie-Mellon {Jniversity, Pittburgh, Pa, 1988.
9. M Lennig, D Sharp, P Kenny, V Gupta and K Precoda. "Flexible vocabulary recognition of speech", Proc. Int. Conf. on Spoken Language Processing, pp 93-96, Banff, Canada, 12-16 October 1992.
10. R K Moore, "Context Adaptive Phone (CAP) Modelling for Automatic Speech Recognition", DRA Malvern Memorandum No. 4751, March 1993.
11. B Plannerer and G Ruske, "Recognition of demisyllable based units using semicontinuous hidden Markov models", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp I- 581-584. San Francisco, 23-26 March 1992.
12. E Schukat-Talamazzini, H Niemann, W Eckert, T Kuhn and S. Rieck, "Acoustic modelling of subword units in the ISADORA speech recogniser", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp 1-577-580, San Francisco, 23-26 March 1992.
13. R M Schwartz, Y L Chow, 0 A Kimball, S Roucos, M Krasner and J Makhoul, "Contextdependent modelling for acoustic-phonetic recognition of continuous speech", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 1985.
14. L C Wood, D J Pierce and F Novello, "Improved vocabulary-independent sub-word HMM modelling", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp 181-184, Toronto, 14-17 May 1991.