Cross-language bootstrapping for unsupervised acoustic model training: Rapid development of a polish speech recognition system

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 88-91

  Lööf, Jonas ^a   Gollan, Christian ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Cross language bootstrapping; Speech recognition; Unsupervised training

Indexed keywords

ACOUSTIC MODEL; ADAPTIVE TRAINING; AUDIO DATA; EUROPEAN PARLIAMENT; MAXIMUM LIKELIHOOD LINEAR REGRESSION; MODEL TRAINING; RAPID DEVELOPMENT; SPEECH RECOGNITION SYSTEMS; SYSTEM DEVELOPMENT; TRAINING DATA; UNSUPERVISED TRAINING; VOCAL TRACT LENGTH NORMALIZATION;

ACOUSTICS; LINGUISTICS; MAXIMUM LIKELIHOOD; REFINING; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 70450181523     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Zavaliagkos, G. and Colthurst, T., "Utilizing untranscribed training data to improve performance," in DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, VA, USA, Feb. 1998, pp. 301 - 305.
2. Gollan, C. and Ney, H., "Towards automatic learning in LVCSR: Rapid development of a Persian transcription system," in Proc. Int. Conf. on Spoken Language Processing, Sep. 2008, pp. 1441 - 1444.
3. Ma, J., Matsoukas, S., Kimball, O., and Schwartz, R., "Unsupervised training on large amounts of broadcast news data," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 3, Toulouse, France, May 2006, pp. 1057 - 1059.
4. Ramabhadran, B., "Exploiting large quantities of spontaneous speech for unsupervised training of acoustic models," in Proc. Int. Conf. on Spoken Language Processing, Lisbon, Portugal, 2005, pp. 1617-1620.
5. Gollan, C., Hahn, S., Schlüter, R., and Ney, H., "An improved method for unsupervised training of LVCSR systems," in Interspeech, Antwerp, Belgium, Aug. 2007, pp. 2101-2104.
6. Wessel, F. and Ney, H., "Unsupervised training of acoustic models for large vocabulary continuous speech recognition," IEEE Trans. on Speech and Audio Processing, vol. 13, no. 1, pp. 23 - 31, Jan. 2005.
7. Wessel, F., Macherey, K., and Ney, H., "A comparison of word graph and N-best list based confidence measures," in European Conference on Speech Communication and Technology, Budapest, Hungary, Sep. 1999, pp. 315-318.
8. Evermann, G. andWoodland, P., "Large vocabulary decoding and confidence estimation using word posterior probabilities," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Istanbul, Turkey, Jun. 2000, pp. 1655 - 1658.
9. Gollan, C. and Bacchiani, M., "Confidence scores for acoustic model adaptation," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Las Vegas, NV, USA, Mar. 2008, pp. 4289 - 4292.
10. Schultz, T. and Waibel, A., "Experiments on cross-language acoustic modeling," in Proc. European Conf. on Speech Communication and Technology, Aalborg, Denmark, Sep. 2001, pp. 2721 - 2724.
11. Marasek, K., "Polish LVCSR in the Janus system. Preliminary results for the SpeeCon database," Archives of Acoustics, vol. 32, no. 1, pp. 119 - 126, 2007.
12. Loquendo, "New Language for Loquendo ASR: Polish," 2006 http://www.loquendo.com/en/news/news loquendo ASR polish.htm.
13. Demenko, G., Grocholewski, S., Klessa, K., Ogórkiewicz, J., Wagner, A., Lange, M., Śledziński, D., and Cylwik, N., "JURISDIC - Polish speech database for taking dictation of legal texts," Atlanta, GA, USA, May 2008, pp. 1280 - 1287.
14. "JUMAS, Judicial Management by Digital Libraries Semantics," http://www.jumasproject.eu.
15. Lööf, J., Bisani, M., Gollan, C., Heigold, G., Hoffmeister, B., Plahl, C., Schlüter, R., and Ney, H., "The 2006 RWTH parliamentary speeches transcription system," in Proc. Int. Conf. on Spoken Language Processing, Pittsburgh, PA, USA, Sep. 2006, pp. 105 - 108.
16. Lööf, J., Gollan, C., Hahn, S., Heigold, G., Hoffmeister, B., Plahl, C., Rybach, D., Schlüter, R., and Ney, H., "The RWTH 2007 TC-STAR evaluation system for European English and Spanish," in Proc. Int. Conf. on Spoken Language Processing, Antwerp, Belgium, Aug. 2007, pp. 2145 - 2148.
17. Gollan, C., Bisani, M., Kanthak, S., Schlüter, R., and Ney, H., "Cross domain automatic transcription on the TC-STAR EPPS corpus," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 1, Philadelphia, PA, Mar. 2005, pp. 825-828.
18. Oliver, D., "Polish text to speech synthesis," Master's thesis, Edinburgh University, Edinburgh, UK, 1998.
19. Siegler, M. A., Jain, U., Raj, B., and Stern, R. M., "Automatic segmentation, classification and clustering of broadcast news audio," in Proc. DARPA Speech Recognition Workshop, 1997, pp. 97-99.