Investigation of multilingual deep neural networks for spoken term detection

2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

Volumn , Issue , 2013, Pages 138-143

  Knill, K M ^a   Gales, M J F ^a   Rath, S P ^a   Woodland, P C ^a   Zhang, C ^a   Zhang, S X ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

keyword search; Multilingual; neural networks; speech recognition; spoken term detection

Indexed keywords

BOTTLENECK FEATURES; DEEP NEURAL NETWORKS; KEYWORD SEARCH; LANGUAGE INDEPENDENTS; MULTILINGUAL; MULTILINGUAL APPROACH; SPOKEN TERM DETECTIONS; TANDEM CONFIGURATION;

COMPUTATIONAL LINGUISTICS; DECISION TREES; HYBRID SYSTEMS; SEARCH ENGINES; SPEECH RECOGNITION;

NEURAL NETWORKS;

EID: 84893668957     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2013.6707719     Document Type: Conference Paper

References (34)

1. Mary Harper, IARPA Babel Program, http://www.iarpa.gov/Programs/ia/Babel/ babel.html.
2. H. Hermansky, D. Ellis, and S. Sharma, Tandem Connectionist Feature Extraction for Conventional HMM Systems, in Proc. ICASSP, 2000.
3. Y Bengio, Learning deep architectures for AI, Found. Trends Mach. Learn., vol. 2, pp. 1-127, 2009.
4. H. Bourlard et al., Current trends in multilingual speech processing, Sadhana, vol. 36, pp. 885-915, 2011.
5. Frantisek Grezl et al., Probabilistic and bottle-neck features for LVCSR of meetings, in Proc. ICASSP, 2007.
6. Samuel Thomas, Sriram Ganapathy, and Hynek Hermansky, Cross-lingual and multi-stream posterior features for lowresource LVCSR systems, in Proc. Interspeech, 2010.
7. David Imseng, Herve Bourlard, and Mathew Magimai-Doss, Towards mixed language speech recognition systems, in Proc. Interspeech, 2010.
8. Samuel Thomas, Sriram Ganapathy, and Hynek Hermansky, Multilingual MLP features for low-resource LVCSR systems, in Proc. ICASSP, 2012.
9. Zoltan Tuske et al., Investigation on cross- And multilingual MLP features under matched and mismatched acoustical conditions, in Proc. ICASSP, 2013.
10. H. A. Bourlard and N.Morgan, Connectionist Speech Recogni- Tion: A Hybrid Approach, Kluwer Academic Publishers, Norwell, MA, USA, 1993.
11. Stefano Scanzio et al., On the use of a multilingual neural network front-end, in Proc. Interspeech, 2008.
12. Arnab Ghoshal, Pawel Swietojanski, and Steve Renals, Multilingual training of deep neural networks, in Proc. ICASSP, 2013.
13. Jui-Ting Huang et al., Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers, in Proc. ICASSP, 2013.
14. Georg Heigold et al., Multilingual acoustic models using distributed deep neural networks, in Proc. ICASSP, 2013.
15. Andreas Stolcke et al., Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons, in Proc. ICASSP, 2006.
16. Tanja Schultz and AlexWaibel, Fast bootstrapping of LVCSR systems with multilingual phoneme sets, in Proc. Eurospeech, 1997.
17. Stephane Dupont et al., Feature extraction and acoustic modeling: An approach for improved generalization across languages and accents, in Proc. ASRU, 2005.
18. W. Byrne et al., Towards language independent acoustic modeling, in Proc. ICASSP, 2000.
19. Khe Chai Sim and Haizhou Li, Robust phone set mapping using decision tree clustering for cross-lingual phone recognition, in Proc. ICASSP, 2008.
20. Karel Vesely et al., The language-independent bottleneck features, in Proc. SLT, 2012.
21. Frantisek Grezl, Martin Karafiat, and Milos Janda, Study of probabilistic and bottle-neck features in multilingual environment, in Proc. ASRU, 2011.
22. T. Schultz, GlobalPhone: A multilingual speech and text database developed at Karlsruhe Univ., in Proc. ICSLP, 2002.
23. J. G. Fiscus et al., Results of the 2006 Spoken Term Detection Evaluation, in Proc. ACM SIGIR Workshop on Searching Spontaneous Conversational Speech, 2007.
24. 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.
25. Daniel Povey et al., fMPE: Discriminatively trained features for speech recognition, in Proc. ICASSP, 2005.
26. 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.
27. G. Hinton, L. Deng, et al., Deep Neural Networks for Acoustic Modeling in Speech Recognition, Signal Processing Mag- Azine, IEEE, vol. 29, no. 6, pp. 82-97, Nov 2012.
28. F. Seide, G. Li, X. Chen, and D. Yu, Feature engineering in context-dependent deep neural networks for conversational speech transcription, in Proc. ASRU, Dec 2011.
29. L. Mangu, H. Soltau, H.-K. Kuo, B. Kingsbury, and G. Saon, Exploiting diversity for spoken term detection, in Proc. ICASSP, 2013.
30. S.M. Siniscalchi et al., Experiments on cross-language attribute detection and phone recognition with minimal targetspecific training data, IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 3, pp. 875-887, 2012.
31. S. J. Young et al., The HTK Book (for HTK version 3.4), Cambridge University, 2006.
32. David Johnson et al., QuickNet, http://www1.icsi.berkeley.edu/Speech/qn. html.
33. A. Stolcke, SRILM - An Extensible Language Modeling Toolkit, in Proc. ICSLP, 2002.
34. B. Kingsbury et al., A high-performance Cantonese keyword search system, in Proc. ICASSP, 2013.