Unsupervised adaptation of categorical prosody models for prosody labeling and speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 17, Issue 1, 2009, Pages 138-149

  Ananthakrishnan, Sankaranarayanan ^a,b   Narayanan, Shrikanth ^a  

^a University of Southern California   (United States)

^b BBN TECHNOLOGIES   (United States)

Author keywords

Categorical prosody models; Lattice enrichment speech recognition; Unsupervised adaptation

Indexed keywords

ACOUSTIC COMPONENTS; ACOUSTIC MODEL; AUTOMATIC SPEECH RECOGNITION SYSTEM; BASELINE SYSTEMS; BOSTON UNIVERSITY; BREAK INDICES; CATEGORICAL PROSODY MODELS; CLASSIFICATION ERROR RATE; HUMAN SPEECH; LATTICE ENRICHMENT SPEECH RECOGNITION; PITCH ACCENTS; PROSODY LABELING; PROSODY MODEL; RELATIVE REDUCTION; SEED MODEL; SPEECH RECOGNIZER; UNSUPERVISED ADAPTATION; WORD ERROR RATE;

ACOUSTICS; CONCENTRATION (PROCESS); LINGUISTICS; REMELTING; SOFTWARE AGENTS; SYNTACTICS;

SPEECH RECOGNITION;

EID: 70350458869     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2008.2005347     Document Type: Article

References (25)

1. K. Silverman, M. Beckman, J. Pitrelli, M. Ostendorf, C.Wightman, P. Price, J. Pierrehumbert, and J. Hirschberg, "ToBI: A standard scheme for labeling prosody," in Proc. Int. Conf. Spoken Lang. Process., 1992, pp. 867-869.
2. D. Hirst and A. D. Cristo, , D. Hirst and A. D. Cristo, Eds., Intonation Systems: A Survey of Twenty Languages. Cambridge, U.K.: Cambridge Univ. Press, 1998.
3. E. Grabe, F. Nolan, and K. Farrar, "IViE-A comparative transcription system for intonational variation in English," in Proc. Int. Conf. Spoken Lang. Process., 1998, pp. 1259-1262.
4. S. Ananthakrishnan and S. Narayanan, "Automatic prosodic event detection using acoustic, lexical, and syntactic evidence," IEEE Trans. Audio, Speech, Lang. Process., vol.16, no.1, pp. 216-228, Jan. 2008.
5. M. Ostendorf, I. Shafran, and R. Bates, "Prosody models for conversational speech recognition," in Proc. 2nd Plenary Meeting Symp. Prosody and Speech Process., 2003, pp. 147-154.
6. C. Wang and S. Seneff, "Lexical stress modeling for improved speech recognition of spontaneous telephone speech in the JUPITER domain," in Proc. 7th Eur. Conf. Speech Commun. Technol., 2001, pp. 2761-2764.
7. M. Hasegawa-Johnson, J. Cole, C. Shih, K. Chen, A. Cohen, S. Chavarria, H. Kim, T. Yoon, S. Borys, and J.-Y. Choi, "Speech recognition models of the interdependence among syntax, prosody and segmental acoustics," in Proc. HLT/NAACL, 2004, pp. 56-63.
8. K. Chen, M. Hasegawa-Johnson, A. Cohen, S. Borys, S.-S. Kim, J. Cole, and J.-Y. Choi, "Prosody dependent speech recognition on radio news corpus of American english," IEEE Trans. Speech, Audio, Lang. Process., vol.14, no.1, pp. 232-245, Jan. 2006.
9. M. Ostendorf, P. Price, and S. Shattuck-Hufnagel, "The Boston University Radio News Corpus," Boston Univ., Boston, MA, Tech. Rep. ECS-95-1001, Mar. 1995.
10. S. Ananthakrishnan and S. Narayanan, "Improved speech recognition using acoustic and lexical correlates of pitch accent in a N-best rescoring framework," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2007, pp. 873-876.
11. S. Ananthakrishnan and S. Narayanan, "Prosody-enriched lattices for improved syllable recognition," in Proc. Int. Conf. Spoken Lang. Process., Antwerp, Belgium, Sep. 2007.
12. A. Syrdal, J. Hirschberg, J. McGory, and M. Beckman, "Automatic ToBI prediction and alignment to speed manual labeling of prosody," Speech Commun., vol.33, pp. 135-151, 2001.
13. C. Nakatani, J. Hirschberg, and B. Grosz, "Discourse structure in spoken language: Studies on speech corpora," in Proc. AAAI Spring Symp. Empirical Methods in Discourse Interpretation and Generation, Mar. 1995, pp. 106-112.
14. G. Ferguson, J. Allen, B. Miller, and E. Ringger, "The design and implementation of the TRAINS-96 system: A prototype mixed-initiative planning assistant," Univ. of Rochester, Rochester, Tech. Rep. TN96-5, Oct. 1996.
15. M. Ostendorf, I. Shafran, S. Shattuck-Hufnagel, L. Carmichael, and W. Byrne, "A prosodically labeled database of spontaneous speech," in Proc. ISCA Workshop Prosody in Speech Recognition and Understanding, Oct. 2001, pp. 119-121.
16. S. Ananthakrishnan and S. Narayanan, "A novel algorithm for unsupervised prosodic language model adaptation," in Proc. Int. Conf. Acoust. , Speech Signal Process., Las Vegas, NV, 2008.
17. "CSR-II (WSJ1) Complete," Linguistic Data Consortium, Philadelphia, PA, 1994.
18. B. Pellom, "SONIC: The University of colorado continuous speech recognizer," Univ. of Colorado, Boulder, CO, Tech. Rep. TR-CSLR- 2001-2101, Mar. 2001.
19. A. Stolcke, "SRILM-An extensible language modeling toolkit," in Proc. Int. Conf. Spoken Lang. Process., Denver, CO, 2002, vol.2, pp. 901-904.
20. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus in speech recognition: Word error minimization and other applications of confusion networks," Computer, Speech, Lang., vol.14, no.4, pp. 373-400, 2000.
21. G. Evermann, "Minimum word error rate decoding," M.S. thesis, Cambridge Univ., Cambridge, U.K., 1999.
22. J. Bilmes, "A Gentle tutorial on the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models," Univ. of Berkeley, Berkeley, CA, Tech. Rep. ICSI-TR-97- 021, 1997.
23. J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol.2, no.2, pp. 291-298, Apr. 1994.
24. J.-L. Gauvain and C.-H. Lee, "Bayesian learning of Gaussian mixture densities for hidden Markov models," in Proc. DARPA Speech and Natural Language Workshop, Pacific Grove, CA, 1991, pp. 272-277, Morgan-Kaufmann.
25. S. Young, G. Evermann, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland, The HTK Book. Cambridge, U.K.: Cambridge Univ., Dec. 2002.