Cross-lingual transfer learning during supervised training in low resource scenarios

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

Volumn 2015-January, Issue , 2015, Pages 3531-3535

  Das, Amit ^a   Hasegawa Johnson, Mark ^a  

^a United States of America   (United States)

Author keywords

Cross lingual speech recognition; Deep neural networks; Hidden Markov models; Transfer learning

Indexed keywords

COMPUTATIONAL LINGUISTICS; GAUSSIAN DISTRIBUTION; HIDDEN MARKOV MODELS; MARKOV PROCESSES; MAXIMUM LIKELIHOOD; NATURAL LANGUAGE PROCESSING SYSTEMS; SPEECH COMMUNICATION; TRELLIS CODES;

CONTEXT DEPENDENT; CROSS-LINGUAL SPEECH RECOGNITION; DEEP BELIEF NETWORK (DBN); DEEP NEURAL NETWORKS; GAUSSIAN MIXTURE MODEL; SEQUENTIAL MANNERS; SUPERVISED TRAININGS; TRANSFER LEARNING;

SPEECH RECOGNITION;

EID: 84959115246     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (23)

1. B. Wheatley, K. Kondo, W. and erson, and Y. Muthusamy, "Anevaluation of cross-language adaptation for rapid HMM developmentin a new language, " in ICASSP.
2. T. Schultz and A. Waibel, "Fast bootstrapping of LVCSR systemswith multilingual phoneme sets, " in Eurospeech., 1997.
3. J. Kohler, "Language adaptation of multilingual phone modelsfor vocabulary independent speech recognition tasks, " in ICASSP., 1998, vol. 1, pp. 417-420.
4. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependentpre-trained deep neural networks for large-vocabulary speechrecognition, " IEEE Trans. Audio, Speech, Lang. Process., vol. 20, no. 1, pp. 30-42, Jan 2012.
5. A. Stolcke, F. Grezl, M.-Y. Hwang, X. Lei, N. Morgan, and D. Vergyri, "Cross-domain and cross-lingual portability of acousticfeatures estimated by multilayer perceptrons, " in ICASSP., 2006, pp. 321-324.
6. S. Thomas, S. Ganapathy, and H. Hermansky, "Cross-lingual and multi-stream posterior features for low resource LVCSR systems, "in Interspeech, 2010.
7. F. Grézl, M. Karafiát, S. Kontár, and J. Cernocký, "Probabilisticand bottle-neck features for LVCSR of meetings, " in ICASSP., 2007.
8. S. Thomas, S. Ganapathy, and H. Hermansky, "Multilingual MLPfeatures for low-resource LVCSR systems, " in ICASSP., 2012.
9. P. Swietojanski, A. Ghoshal, and S. Renals, "Unsupervised crosslingualknowledge transfer in DNN-based LVCSR, " in IEEE SLTWorkshop, 2012.
10. J.-T. Huang, J. Li, D. Yu, L. Deng, and Y. Gong, "Cross languageknowlege transfer using multilingual deep neural network withshared hidden layers, " in ICASSP., 2013.
11. A. Ghoshal, P. Swietojanski, and S. Renals, "Multilingual trainingof deep neural networks, " in ICASSP., 2013.
12. N. Vu, W. Breiter, F. Metze, and T. Schultz, "An investigationon initialization schemes for multilayer perceptron training usingmultilingual data and their effect on ASR performance, " in Interspeech, 2012.
13. J.-T. Huang, "Semi-supervised learning for acoustic and prosodicmodeling in speech applications, " Ph. D. dissertation, Universityof Illinois at Urbana-Champaign, 2012. [Online]. Available: http: //www. isle. illinois. edu/sst/pubs/2012/huang12thesis. pdf
14. J.-T. Huang and M. Hasegawa-Johnson, "On semi-supervisedlearning of Gaussian mixture models for phonetic classification, "in NAACL HLT Workshop on Semi-Supervised Learning, 2013.
15. P. Huang and M. Hasegawa-Johnson, "Cross-dialectal data transferringfor Gaussian mixture model training in Arabic speechrecognition, " 4th International Conference on Arabic LanguageProcessing, pp. 119-123, 2012.
16. L. R. Rabiner, "A tutorial on hidden Markov models and selectedapplications in speech recognition, " Proceedings of the IEEE, vol. 77, no. 2, pp. 257-286, 1989.
17. Ö zgül Salor and M. Demirekler, "On developing new text and audio corpora and speech recognition tools for the Turkish language, "in International Conf. Spoken Language Processing, 2002, pp. 349-352.
18. J. L. Hieronymus, "ASCII phonetic symbols for the world's languages: WORLDBET, " J. Int. Phonetic Association, 1993.
19. R. Gopinath, "Maximum likelihood modeling with Gaussian distributionsfor classification, " in ICASSP., 1998, pp. 661-664.
20. M. J. F. Gales, "Maximum likelihood linear transformations forHMM-based speech recognition, " Computer Speech and Language., vol. 12.
21. K.-F. Lee and H.-W. Hon, "Speaker-independent phone recognitionusing hidden Markov models, " IEEE Trans. Acoust., Speech, Signal Process., vol. 37, no. 11, pp. 1641-1648, November 1989.
22. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlcek, Y. Qian, P. Schwarz, J. Silovský, G. Stemmer, and K. Veselý, "The Kaldi speech recognitiontoolkit, " in IEEE ASRU Workshop., 2011.
23. T. Schultz and A. Waibel, "Language independent and languageadaptive acoustic modeling for speech recognition, " vol. 35, pp. 31-51, Aug 2001.