BOOSTING UNDER-RESOURCED SPEECH RECOGNIZERS BY EXPLOITING OUT OF LANGUAGE DATA - CASE STUDY ON AFRIKAANS

3rd Workshop on Spoken Language Technologies for Under-Resourced Languages, SLTU 2012

Volumn , Issue , 2012, Pages 60-67

  Imseng, David ^a,b   Bourlard, Hervé ^a,b   Garner, Philip N ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b EPFL   (Switzerland)

Author keywords

Afrikaans; Multilingual speech recognition; posterior features; under resourced languages

Indexed keywords

SPEECH RECOGNITION;

AFRIKAAN; CASE-STUDIES; MULTILAYERS PERCEPTRONS; MULTILINGUAL SPEECH RECOGNITION; PERFORMANCE; POSTERIOR FEATURES; SPEECH RECOGNIZER; TARGET LANGUAGE; UNDER-RESOURCED; UNDER-RESOURCED LANGUAGES;

ACOUSTIC MODELING;

EID: 84883358833     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. D. Imseng, H. Bourlard, and P. N. Garner, “Using KL-divergence and multilingual information to improve ASR for under-resourced languages,” in Proc. of ICASSP, 2012, pp. 4869-4872.
2. Y. Qian, J. Xu, D. Povey, and J. Liu, “Strategies for using MLP based features with limited target-language training data,” in Proc. of ASRU, 2011, pp. 354-358.
3. T. Niesler, “Language-dependent state clustering for multilingual acoustic modelling,” Speech Communication, vol. 49, pp. 453-463, 2007.
4. T. Schultz and A. Waibel, “Language-independent and language-adaptive acoustic modeling for speech recognition,” Speech Communication, vol. 35, pp. 31-51, 2001.
5. Leonard Bloomfield, Language, New York: Holt, 1933.
6. D. Imseng, H. Bourlard, J. Dines, P. N. Garner, and M. Magimai.-Doss, “Improving non-native ASR through stochastic multilingual phoneme space transformations,” in Proc. of Interspeech, 2011, pp. 537-540.
7. Vàclav Blažek, “On the internal classification of Indo-European languages: survey,” 2005, http://www.phil.muni.cz/linguistica/art/blazek/bla-003.pdf.
8. A. Constantinescu and G. Chollet, “On cross-language experiments and data-driven units for ALISP (automatic language independent speech processing),” in Proc. of ASRU, 1997, pp. 606-613.
9. W. Heeringa and F. de Wet, “The origin of Afrikaans pronunciation: a comparison to west Germanic languages and Dutch dialects,” in Proc. of the Conf. of the Pattern Recognition Association of South Africa, 2008, pp. 159-164.
10. H. Hermansky, D.P.W. Ellis, and S Sharma, “Tandem connectionist feature extraction for conventional HMM systems,” in Proc. of ICASSP, 2000, pp. III-1635-1638.
11. G. Aradilla, H. Bourlard, and M. Magimai-Doss, “Using KL-based acoustic models in a large vocabulary recognition task,” in Proc. of Interspeech, 2008, pp. 928-931.
12. L. Tòth, J. Frankel, G. Gosztolya, and S. King, “Cross-lingual portability of MLP-based tandem features - a case study for English and Hungarian.,” in Proc. of Interspeech, 2008, pp. 2695-2698.
13. F. Grézl, M. Karafiàt, and M. Janda, “Study of probabilistic and bottle-neck features in multilingual environment,” in Proc. of ASRU, 2011, pp. 359-364.
14. S. Kullback and R. A. Leibler, “On information and sufficiency,” The Annals of Mathematical Statistics, vol. 22, no. 1, pp. 79-86, 1951.
15. E. Barnard, M. Davel, and C. van Heerden, “ASR corpus design for resource-scarce languages,” in Proc. of Interspeech, 2009, pp. 2847-2850.
16. M. Davel and O. Martirosian, “Pronunciation dictionary development in resource-scarce environments,” in Proc. of Interspeech, 2009, pp. 2851-2854.
17. N. Oostdijk, “The spoken Dutch corpus. Overview and first evaluation.,” in In Proceedings of the Second International Conference on Language Resources and Evaluation, 2000, vol. II, pp. 887-894.
18. D. Imseng, H. Bourlard, and M. Magimai.-Doss, “Towards mixed language speech recognition systems,” in Proc. of Interspeech, 2010, pp. 278-281.
19. Koichi Shinoda and Takao Watanabe, “Acoustic modeling based on the MDL principle for speech recognition,” in Proc. of Eurospeech, 1997, vol. I, pp. 99-102.
20. S. J. Young, J. J. Odell, and P. C. Woodland, “Tree-based state tying for high accuracy acoustic modelling,” in Proceedings of the workshop on Human Language Technology, 1994, pp. 307-312.
21. David Imseng and John Dines, “Decision tree clustering for KL-HMM,” Idiap-Communication Idiap-Com-01-2012, Idiap research institute, 2012.
22. F. Seide, G. Li, and D. Yu, “Conversational speech transcription using context-dependent deep neural networks,” in Proc. of Interspeech, 2011, pp. 437-440.
23. M. Bisani and H. Ney, “Bootstrap estimates for confidence intervals in ASR performance evaluation,” in Proc. of ICASSP, 2004, vol. 1, pp. I-409-412.
24. C. van Heerden, E. Barnard, and M. Davel, “Basic speech recognition for spoken dialogues,” in Proc. of Interspeech, 2009, pp. 3003-3006.