Modelling of phone duration (using the TIMIT database) and its potential benefit for ASR

Speech Communication

Volumn 19, Issue 2, 1996, Pages 161-176

  Pols, Louis C W ^a   Wang, Xue ^a   Ten Bosch, Louis F M ^b  

^a UNIVERSITY OF AMSTERDAM   (Netherlands)

^b NUANCE COMMUNICATIONS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DATABASE SYSTEMS; MATHEMATICAL MODELS; PROBABILITY; SIGNAL PROCESSING;

ANALYSIS OF VARIANCE; PROBABILISTIC ACOUSTIC; RECOGNIZER; TIMIT DATABASE;

SPEECH RECOGNITION;

EID: 0030205397     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-6393(96)00033-7     Document Type: Article

References (42)

1. H. Bourlard, H. Hermansky and N. Morgan (1996), "Towards increasing speech recognition error rates", Speech Communication, Vol. 18, No. 3, pp. 205-231.
2. F. Brugnara, D. Falavigna and M. Omologo (1993), "Automatic segmentation and labeling of speech based on Hidden Markov Models", Speech Communication, Vol. 12, No. 4, pp. 357-370.
3. D. Byrd (1992), "Sex, dialects, and reduction", Proc. ICSLP'92, Banff, Vol. 1, pp. 827-830.
4. M. Chen (1970), "Vowel length variation as a function of the voicing of the consonant environment", Phonetica, Vol. 22, pp. 129-159.
5. T.H. Crystal and A.S. House (1982), "Segmental durations in connected-speech signals: Preliminary results", J. Acoust. Soc. Amer., Vol. 72, pp. 705-716.
6. T.H. Crystal and A.S. House (1988a), "Segmental durations in connected-speech signals: Current results", J. Acoust. Soc. Amer., Vol. 83, pp. 1553-1573.
7. T.H. Crystal and A.S. House (1988b), "Segmental durations in connected-speech signals: Syllabic stress", J. Acoust. Soc. Amer., Vol. 83, pp. 1574-1585.
8. T.H. Crystal and A.S. House (1990), "Articulation rate and the duration of syllables and stress groups in connected speech", J. Acoust. Soc. Amer., Vol. 88, pp. 101-112.
9. W. Eefting (1991), Timing in talking. Tempo variation in production and perception, Ph.D. Thesis, University of Utrecht.
10. J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett and N.L. Dahlgren (1993), The DARPA TIMIT acousticphonetic continuous speech corpus CDROM, NTIS order number PB01-100354, now available from LDC.
11. J.L. Gauvain, L.F. Lamel, G. Adda and M. Adda-Decker (1994), "Speaker-independent continuous speech dictation", Speech Communication, Vol. 15, Nos, 1-2, pp. 21-37.
12. M.M. Hochberg and H.F. Silverman (1993), "Constraining the duration variance in HMM-based connected-speech recognition", Proc. Eurospeech'93, Berlin, Vol. 1, pp. 323-326.
13. M. Jones and P.C. Woodland (1993), "Using relative duration in large vocabulary speech recognition", Proc. Eurospeech'93, Berlin, Vol. 1, pp. 311-314.
14. P.A. Keating, D. Byrd, E. Flemming and Y. Todaka (1994), "Phonetic analyses of word and segment variation using the TIMIT corpus of American English", Speech Communication, Vol. 14, No. 2, pp. 131-142.
15. D.H. Klatt (1987), "Review of text-to-speech conversion for English", J. Acoust. Soc. Amer., Vol. 82, pp. 737-793.
16. L.F. Lamel and J.L. Gauvain (1993a), "Identifying non-linguistic speech features", Proc. Eurospeech'93, Berlin, Vol. 1, pp. 23-30.
17. L.F. Lamel and J.L. Gauvain (1993b), "High performance speaker-independent phone recognition using CDHMM", Proc. Eurospeech'93, Berlin, Vol. 1, pp. 121-124.
18. L. Lamel, R. Kassel and S. Seneff (1986), "Speech database development: Design and analysis of the acoustic-phonetic corpus", Proc. DARPA Speech Recognition Workshop, pp. 100-109.
19. K.-F. Lee and H.-W. Hon (1989), "Speaker-independent phone recognition using Hidden Markov Models", IEEE Trans. Acoust. Speech Signal Process., Vol. ASSP-37, pp. 1641-1648.
20. S.E. Levinson (1986), "Continuously variable duration hidden Markov models for automatic speech recognition", Computer Speech and Language, Vol. 1, pp. 29-45.
21. A. Ljolje (1994), "High accuracy phone recognition using context clustering and quasi-triphone models", Computer Speech and Language, Vol. 8, pp. 129-151.
22. A. Ljolje and M.D. Riley (1991), "Automatic segmentation and labeling of speech", Proc. Internat. Conf. Acoust. Speech Signal Process.-91, Toronto, pp. 473-476.
23. S.G. Nooteboom (1970), Production and perception of vowel duration, Ph.D. Thesis, University of Utrecht.
24. O.K. Oller (1973), "The effect of position in utterance on speech segment duration in English", J. Acoust. Soc. Amer., Vol. 54, pp. 1235-1247.
25. D. Pallett (1990), "Speech corpora and performance assessment in the DARPA SLS program", Proc. ICSLP'90, Kobe, pp. 24.3.1-24.3.4.
26. D.S. Pallett, J.G. Fiscus, W.M. Fisher, J.S. Garofolo, B.A. Lund, A. Martin and M.A. Przybocki (1995), "1994 Benchmark tests for the ARPA Spoken Language Program", Proc. ARPA Spoken Language Systems Technology Workshop, Austin, TX, pp. 5-36.
27. G.E. Peterson and I. Lehiste (1960), "Duration of syllable nuclei in English", J. Acoust. Soc. Amer., Vol. 32, pp. 693-703.
28. T. Robinson (1991), Several improvements to a recurrent error propagation network phone recognition system, Technical report, Cambridge Univ., CUED/F-INFENG/TR.82.
29. D.X. Sun and L. Deng (1995), "Analysis of acoustic-phonetic variations in fluent speech using TIMIT", Proc. Internat. Conf. Acoust. Speech Signal Process.-95, Detroit, pp. 201-204.
30. N. Umeda (1975), "Vowel duration in American English", J. Acoust. Soc. Amer., Vol. 58, pp. 434-445.
31. V.J. Van Heuven and L.C.W. Pols, Eds. (1993), Analysis and Synthesis of Speech. Strategic Research towards high-quality Text-to-speech Generation (Mouton/De Gruyter, Berlin).
32. J.P.H. Van Santen (1992), "Contextual effects on vowel duration", Speech Communication, Vol. 11, No. 6, pp. 513-546.
33. R.J.J.H. Van Son (1993), Spectro-temporal features of vowel segments, Studies in Language and Language Use 3, Ph.D. thesis, University of Amsterdam.
34. A. Vorstermans, J.P. Martens and B. Van Coile (1995), "Fast automatic segmentation and labeling: Results on TIMIT and EUROM0", Proc. Eurospeech'95, Madrid, Vol. 2, pp. 1397-1400.
35. X. Wang (1994), "Durationally constrained training of HMM without explicit state durational pdf", Proc. Inst. Phonetic Sciences Univ. of Amsterdam, Vol. 18, pp. 111-130.
36. X. Wang (1995), "Durational modelling in HMM-based speech recognition: Towards a justified measure", in: A.J. Rubio and J.M. López, Eds., Speech Recognition and Coding. New Advances and Trends (Springer, Berlin), pp. 128-131.
37. X. Wang (1996), Duration modelling in HMM-based speech recognition, Ph.D. thesis, University of Amsterdam.
38. P.C. Woodland and S.J. Young (1993), ́The HTK tied-state continuous speech recogniser", Proc. Eurospeech'93, Berlin, Vol. 3, pp. 2207-2210.
39. S.J. Young (1992), HTK Version 1.4: User, reference and programmer manual, Cambridge University Engineering Department, Speech Group, September 1992.
40. S.J. Young and P.C. Woodland (1993), "The use of state tying in continuous speech recognition", Proc. Eurospeech'93, Berlin, Vol. 3, pp. 2203-2206.
41. S.J. Young and P.C. Woodland (1994), "State clustering in hidden Markov model-based continuous speech recognition", Computer Speech and Language, Vol. 8, pp. 369-383.
42. V. Zue, S. Seneff and J. Glass (1990), "Speech database development at MIT: TIMIT and beyond", Speech Communication, Vol. 9, No. 4, pp. 351-356.