SEMI-SUPERVISED LEARNING FOR SPEECH RECOGNITION IN THE CONTEXT OF ACCENT ADAPTATION

Machine Learning in Speech and Language Processing, MLSLP 2012

Volumn , Issue , 2012, Pages 13-17

  Nallasamy, Udhyakumar ^a   Metze, Florian ^a   Schultz, Tanja ^a,b  

^a Carnegie Mellon University ^*  (United States)

^b KARLSRUHE INSTITUTE OF TECHNOLOGY   (Germany)

Author keywords

Accent adaptation; Automatic speech recognition; Semi supervised learning

Indexed keywords

SPEECH RECOGNITION; SUPERVISED LEARNING;

ACCENT ADAPTATION; ACCENTED SPEECH; AUTOMATIC SPEECH RECOGNITION; AUTOMATIC SPEECH RECOGNITION SYSTEM; BROADCAST NEWS; SEMI-SUPERVISED LEARNING; STATE OF THE ART; TRAINING DATA; UNDER-REPRESENTED; WORD ERROR RATE;

LEARNING ALGORITHMS;

EID: 85074733047     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. Hagen Soltau, Lidia Mangu, and Fadi Biadsy, "From modern standard arabic to levantine asr: Leveraging gale for dialects," in ASRU, 2011, pp. 266-271.
2. Udhyakumar Nallasamy, Florian Metze, and Tanja Schultz, "Enhanced polyphone decision tree adaptation for accented speech recognition," in INTERSPEECH, 2012.
3. Fadi Biadsy, Pedro Moreno, and Martin Jansche, "Google's cross-dialect arabic voice search," in ICASSP, 2012.
4. Kai Yu, Mark J. F. Gales, Lan Wang, and Philip C. Woodland, "Unsupervised training and directed manual transcription for LVCSR," Speech Communication, vol. 52, no. 7-8, pp. 652-663, 2010.
5. Frank Wessel and Hermann Ney, "Unsupervised training of acoustic models for large vocabulary continuous speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 13, no. 1, pp. 23-31, 2005.
6. Thomas Kemp and Alex Waibel, "Unsupervised training of a speech recognizer: recent experiments," in EUROSPEECH, 1999.
7. Bhuvana Ramabhadran, "Exploiting large quantities of spontaneous speech for unsupervised training of acoustic models," in INTERSPEECH, 2005, pp. 1617-1620.
8. Jeff Z. Ma and Richard M. Schwartz, "Unsupervised versus supervised training of acoustic models," in INTERSPEECH, 2008, pp. 2374-2377.
9. Jonas Lööf, Christian Gollan, and Hermann Ney, "Crosslanguage bootstrapping for unsupervised acoustic model training: rapid development of a polish speech recognition system," in INTERSPEECH, 2009, pp. 88-91.
10. Scott Novotney, Richard M. Schwartz, and Sanjeev Khudanpur, "Unsupervised arabic dialect adaptation with selftraining," in INTERSPEECH, 2011, pp. 541-544.
11. Wikipedia, "Dialect," http://en.wikipedia.org/ wiki/Dialect.
12. Lidia Mangu, Eric Brill, and Andreas Stolcke, "Finding consensus in speech recognition: word error minimization and other applications of confusion networks," Computer Speech & Language, vol. 14, no. 4, pp. 373-400, 2000.
13. Dong Yu, Balakrishnan Varadarajan, Li Deng, and Alex Acero, "Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion," Computer Speech & Language, vol. 24, no. 3, pp. 433-444, 2010.
14. Thiago Fraga-Silva, Jean-Luc Gauvain, and Lori Lamel, "Lattice-based unsupervised acoustic model training," in ICASSP, 2011, pp. 4656-4659.
15. John Blitzer and Hal Daumé III, "ICML tutorial on domain adaptation," http://adaptationtutorial. blitzer.com, June 2010.
16. Corinna Cortes, Mehryar Mohri, Michael Riley, and Afshin Rostamizadeh, "Sample selection bias correction theory," in ALT, 2008, pp. 38-53.
17. Robert C. Moore and William Lewis, "Intelligent selection of language model training data," in ACL (Short Papers), 2010, pp. 220-224.
18. Jean-Luc Gauvain and Chin-Hui Lee, "Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains," IEEE Transactions on Speech and Audio Processing, vol. 2, no. 2, pp. 291-298, 1994.
19. Daniel Povey and Kaisheng Yao, "A basis representation of constrained mllr transforms for robust adaptation," Computer Speech & Language, vol. 26, no. 1, pp. 35-51, 2012.
20. Florian Metze, Roger Hsiao, Qin Jin, Udhyakumar Nallasamy, and Tanja Schultz, "The 2010 cmu gale speech-to-text system," in INTERSPEECH, 2010, pp. 1501-1504.
21. Xiaodong Cui, Jing Huang, and Jen-Tzung Chien, "Multi-view and multi-objective semi-supervised learning for hmm-based automatic speech recognition," IEEE Transactions on Audio, Speech and Language processing, vol. 20, no. 7, pp. 1923-1935, 2012.
22. Avishek Saha, Piyush Rai, Hal Daumé III, Suresh Venkatasubramanian, and Scott L. DuVall, "Active supervised domain adaptation," in ECML/PKDD (3), 2011, pp. 97-112.
23. Giuseppe Riccardi and Dilek Hakkani-Tür, "Active learning: theory and applications to automatic speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 13, no. 4, pp. 504-511, 2005.
24. N. Itoh, T.N. Sainath, D.N. Jiang, J. Zhou, and B. Ramabhadran, "N-best entropy based data selection for acoustic modeling," in ICASSP, 2012, pp. 4133-4136.