Specifics of hidden Markov model modifications for large vocabulary continuous speech recognition

Informatica

Volumn 15, Issue 1, 2004, Pages 93-110

  Šilingas, Darius ^a   Telksnys, Laimutis ^a  

^a VYTAUTAS MAGNUS UNIVERSITY   (Lithuania)

Author keywords

Beam search; Context dependent phones; Gaussian mixture; Hidden Markov model; HTK; Language modeling; Large vocabulary continuous speech recognition; Viterbi recognition; WSJCAM0

Indexed keywords

EID: 2442568133     PISSN: 08684952     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (18)

1. Clarkson, P.R., and R. Rosenfeld (1997). Statistical language modeling using the CMU Cambridge toolkit. In Proceedings EuroSpeech '97, Rhodes, Greece. http://svr-www.eng.oam.ao.uk/~prc14/eurospeech97.ps
2. Cole, R., J. Mariani, H. Uszkoreit, A. Zaenen, V. Zue, G.B. Varile and A. Zampolli (1998). Survey of the State-of-the-Art in Human Language Technology. Cambridge University Press, Cambridge, UK. http://cslu.ose.ogi.edu/HLTsurvey/ HLTsurvey.html
3. Deller, J.H., J.H.L. Hansen, and J.G. Proakis (1993). Discrete-Time Processing of Speech Signals. Macmillan, New York, USA.
4. Fisher, W.H. (1999). A statistical text-to-phone function using n-grams and rules. In Proceedings IEEE ICASSP'99, vol.2. Phoenix, USA. pp. 649-652. http://www.nist.gov/speech/publications/papersro/ttp4v11.pdf
5. Fransen, J., D. Pye, T. Robinson, Ph. Woodland and S. Young (1994). WSJCAM0 Corpus and Recording Description. Technical report CUED/F-INFENG/TR.192, CUED Speech Group, Cambridge, UK. http://www.Idc.upenn.edu/Catalog/docs/ wsjoam0/wsjoam0.ps
6. Gauvain, J.L., L. Lamel, G. Adda and M. Adda-Decker (1994). The LIMSI Nov93 WSJ System. In Proceedings 1994 ARPA Speech and Natural Language Workshop, Adelaide, Australia. ftp://tip.Iimsi.fr/public/slt94.ps.z
7. Gauvain, J.L., and L. Lamel (1996), Large vocabulary continuous speech recognition: from laboratory systems towards real-world applications. In Transactions of the IEICE, vol. J79-D-II N12. ftp://tip.limsi.fr/public/ieice96. ps.z
8. Jurafsky, D., J.H. Martin and K.V. Linden (2000). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Prentice Hall, New Jersey, USA.
9. Kershaw, D.J. (1996). Phonetic Context-Dependency in a Hybrid ANN/HMM Speech Recognition System. PhD thesis, CUED, Cambridge, UK.
10. Rabiner, L., and B-H. Juang (1993). Fundamentals of Speech Recognition. Prentice Hall, New Jersey, USA.
11. Robinson, T., J. Fransen, D. Pye, J. Foote and S. Renais (1995). WSJCAMO: a british english speech corpus for large vocabulary continuous speech recognition. In Proceedings IEEE ICASSP'95, Detroit, USA. pp. 81-84. http://www.1dc.upenn.edu/Catalog/docs/wsjcam0/abstraot.ps
12. Wegmann, S., F. Scattone, I. Carp, L. Gillick, R. Roth and J. Yamron (1999). Dragon systems' 1997 broadcast news transcription system. In Proceedings 1999 DARPA Broadcast News Workshop, Washington, USA. http://www.nist.gov/ speech/publications/darpa98/pdf/eng150.pdf
13. Woodland, P.C., C.J. Leggetter, J.J. Odell, V. Valtchev and S.J. Young (1995). The development of the 1994 HTK large vocabulary speech recognition system. In Proceedings 1995 ARPA Spoken Language Technology Workshop, Austin, TX, USA. ftp://svr-ftp.eng.cam.ac.uk/pub/reports/woodland_slt95.ps.gz
14. Young, S., N.H. Russell and J.H.S Thornton (1989). Token Passing: a Simple Conceptual Model for Connected Speech Recognition Systems. Technical report CUED/F-INFENG/TR.38, CUED, Cambridge, UK. ftp://svr-ftp.eng.cam.ac.uk/ pub/reports/young_tr38.ps.z
15. Young, S., J. Odell and Ph. Woodland (1994). Tree-based state tying for high accuracy acoustic modeling. In Proceedings ARPA Human Language Technology Conference, Plainsboro, NJ, USA. ftp://svr-ftp.eng.cam.ac.uk/pub/reports/ young_hlt94.ps.z
16. Young, S. (1995). Large vocabulary continuous speech recognition: a review. In Proceedings IEEE Workshop on Speech Recognition, Snowbird, Utah, USA. ftp://svr-ftp.eng.cam.ac.uk/pub/reports/young_LVRreview.ps.gz
17. Young, S.J., and L.L. Chase (1998). Speech recognition evaluation: a review of the U.S. CSR and LVCSR programmes. Computer Speech and Language, 12, 263-279.
18. Young, S., G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, V. Valtchev and Ph. Woodland (2002). Vie HTK Book (for HTK Version 3.2.1). CUED Speech Group, Cambridge, UK. http://htk.eng.cam.ac.uk/prot-doos/htk_book.shtml