Combining tandem and hybrid systems for improved speech recognition and keyword spotting on low resource languages

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

Volumn , Issue , 2014, Pages 835-839

  Rath, Shakti P ^a   Knill, Kate M ^a   Ragni, Anton ^a   Gales, Mark J F ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Deep neural network; Hybrid; Keyword spotting; Tandem

Indexed keywords

DECISION TREES; HYBRID SYSTEMS; SPEECH COMMUNICATION;

AUTOMATIC SPEECH RECOGNITION; CONSISTENT PERFORMANCE; DEEP NEURAL NETWORKS; HYBRID; KEYWORD SPOTTING; LOW RESOURCE LANGUAGES; PERFORMANCE GAIN; TANDEM;

SPEECH RECOGNITION;

EID: 84910068314     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (32)

1. Mary Harper, "IARPA Babel Program, " http://www.iarpa.gov/Programs/ia/Babel/babel.html.
2. G. Hinton, L. Deng, et al., "Deep Neural Networks for Acoustic Modeling in Speech Recognition, " Signal Processing Magazine, IEEE, vol. 29, no. 6, pp. 82-97, Nov 2012.
3. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription, " in Proc. of ASRU, Dec 2011.
4. H. Hermansky, D. Ellis, and S. Sharma, "Tandem Connectionist Feature Extraction for ConventionalHMMSystems, " in Proc. of ICASSP, 2000.
5. Frantisek Grezl, Martin Karafiat, and Milos Janda, "Study of probabilistic and bottle-neck features in multilingual environment, " in Proc. of ASRU, 2011.
6. H. A. Bourlard and N. Morgan, Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers, Norwell, MA, USA, 1993.
7. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recogniser Output Voting Error Reduction (ROVER), " in Proc. of ASRU, 1997.
8. G. Evermann and P. C. Woodland, "Large vocabulary decoding and confidence estimation using word posterior probabilities, " in Proc. of ICASSP 2000.
9. D. R. H. Miller, M. Kleber, et al., "Rapid and accurate spoken term detection, " in Proc. of Interspeech, 2007.
10. D. Vergyri, I. Shafran, et al., "The SRI/OGI 2006 spoken term detection system, " in Proc. of Interspeech, 2007.
11. I. Szoke, L. Burget, J Cernocky, and M. Fapso, "Subword modeling of out of vocabulary words in spoken term detection, " in Proc. of SLT 2008.
12. J. Mamou et al., "System combination and score normalization for spoken term detection, " in Proc. of ICASSP, 2013.
13. L. Mangu, H. Soltau, H.-K. Kuo, B. Kingsbury, and G. Saon, "Exploiting diversity for spoken term detection, " in Proc. of ICASSP, 2013.
14. B. Kingsbury et al., "A high-performance Cantonese keyword search system, " in Proc. of ICASSP, 2013.
15. D. Karakos, R Schwartz, S. Tsakalidis, L. Zhang, et al., "Score normalization and system combination for improved keyword spotting, " in Proc. of ASRU 2013.
16. J. G. Fiscus et al., "Results of the 2006 Spoken Term Detection Evaluation, " in Proc. ACM SIGIR Workshop on Searching Spontaneous Conversational Speech, 2007.
17. S. J. Young, G. Evermann, M. J. F. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. C. Woodland, The HTK Book (for HTK version 3.4.1), Cambridge University, http://htk.eng.cam.ac.uk 2009.
18. David Johnson et al., "QuickNet, " http://www1.icsi.berkeley.edu/Speech/qn.html.
19. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis, " in Proc. of Eurospeech, 1999.
20. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree-based state tying for high accuracy acoustic modelling, " in Proceedings ARPA Workshop on Human Language Technology, 1994, pp. 307-312.
21. Borislava Mimer, Sebastian Stüker, and Tanja Schultz, "Flexible deciscion trees for grapheme based speech recognition, " in Proc. 15th Conference Elektronische Sprachsignalverabeitung (ESSV), Cottbus, Germany, 2004.
22. J. Park et al., "The Efficient Incorporation of MLP Features into Automatic Speech Recognition Systems, " Computer Speech and Language, vol. 25, pp. 519-534, 2010.
23. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markov models, " IEEE Transaction of Speech and Audio Processing, vol. 7, no. 3, pp. 272-281, May 1999.
24. M. J. F. Gales, "Maximum Likelihood Linear Transformations for HMM-Based Speech Recognition, " Computer Speech and Language, vol. 12, no. 2, pp. 75-98, 1998.
25. D. Povey and P. C. Woodland, "Minimum Phone Error and I-smoothing for improved discriminative training, " in Proc. of ICASSP, 2002.
26. D. Povey et al., "fMPE: Discriminatively trained features for speech recognition, " in Proc. of ICASSP, 2005.
27. N. Jaitly and G. E. Hinton, "Vocal tract length perturbation (VTLP) improves speech recognition, " in Proc of ICML, 2013.
28. X. Cui, V. Goel, and B. Kingsbury, "Data augmentation for deep neural network acoustic modeling, " in Proc. of ICASSP, 2014.
29. G. Zavaliagkos and T. Colthurst, "Utilizing untranscribed training data to improve performance, " in Proc. of DARPA Broadcast news transcription and understanding workshop, 1998.
30. L. Lamel and J.-L. Gauvain, "Lightly supervised and unsupervised acoustic model training, " Computer speech and language, vol. 16, pp. 115-129, 2013.
31. M. J. F. Gales, D. Y. Kim, P. C. Woodland, H. Y. Chan, D. Mrva, R. Sinha, and S. E. Tranter, "Progress in the CUHTK broadcast news transcription system, " IEEE Tran ASLP, vol. 14, no. 5, pp. 1513-1525, 2006.
32. M. S. Rasooli, N. Habash, O. Rambow, and T. Lippincott, "Unsupervised morphology-based vocabulary expansion, " in The 52nd Annual Meeting of the Association for Computational Linguistics, 2014.