Improving large vocabulary continuous speech recognition by combining GMM-based and reservoir-based acoustic modeling

2012 IEEE Workshop on Spoken Language Technology, SLT 2012 - Proceedings

Volumn , Issue , 2012, Pages 107-112

  Triefenbach, Fabian ^a   Demuynck, Kris ^a   Martens, Jean Pierre ^a  

^a GHENT UNIVERSITY   (Belgium)

Author keywords

continuous speech recognition; reservoir computing; tandem acoustic modeling

Indexed keywords

ACOUSTIC MODELING; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; PHONEME RECOGNITION; RECOGNITION ACCURACY; RESERVOIR COMPUTING; WORD ERROR RATE REDUCTIONS;

RECURRENT NEURAL NETWORKS; VOCABULARY CONTROL;

CONTINUOUS SPEECH RECOGNITION;

EID: 84874271357     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SLT.2012.6424206     Document Type: Conference Paper

References (19)

1. Herve A. Bourlard and Nelson Morgan, Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers, Norwell, MA, USA, 1993.
2. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional hmm systems," in Proc. of ICASSP, 2000, pp. 1635-1638.
3. Sabato Marco Siniscalchi, Torbjørn Svendsen, and Chin-Hui Lee, "A bottom-up stepwise knowledgeintegration approach to large vocabulary continuous speech recognition using weighted finite state machines," in Proc. of INTERSPEECH, 2011, pp. 901-904.
4. Frank Seide, Gang Li, and Dong Yu, "Conversational speech transcription using context-dependent deep neural networks," in Proc. of INTERSPEECH, 2011, pp. 437-440.
5. G.E. Dahl, Dong Yu, Li Deng, and A. Acero, "Contextdependent pre-trained deep neural networks for largevocabulary speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
6. Li Deng and Dong Yu, "Deep convex net: A scalable architecture for speech pattern classification," in Proc. of INTERSPEECH, 2011, pp. 2285-2288.
7. Li Deng, Dong Yu, and John Platt, "Scalable stacking and learning for building deep architectures," in Proc. of ICASSP, 2012, pp. 2133-2136.
8. Brian Hutchinson, Li Deng, and Dong Yu, "A deep architecture with bilinear modeling of hidden representations: applications to phonetic recognition," in Proc. of ICASSP, 2012, pp. 4805-4808.
9. Herbert Jaeger, "Tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the echo state network approach," Tech. Rep., German National Research Center for Information Technology, 2002.
10. Fabian Triefenbach, Azarakhsh Jalalvand, Benjamin Schrauwen, and Jean-Pierre Martens, "Phoneme recognition with large hierarchical reservoirs," in Proc. Advances in Neural Information Processing Systems (NIPS), 2010, pp. 2307-2315.
11. P.J. Werbos, "Backpropagation through time: what it does and how to do it," Proceedings of the IEEE, vol. 78, no. 10, pp. 1550-1560, oct 1990.
12. Fabian Triefenbach and Jean-Pierre Martens, "Can non-linear readout nodes enhance the performance of reservoir-based speech recognizers?," in Proc. of IEEE Conference on Informatics & Computational Intelligence, 2011, pp. 262-267.
13. Azarakhsh Jalalvand, Fabian Triefenbach, and Jean-Pierre Martens, "Continuous digit recognition in noise: Reservoirs can do an excellent job," in Proc. of INTERSPEECH, 2012.
14. Qifeng Zhu, Barry Chen, Nelson Morgan, and Andreas Stolcke, "On using mlp features in lvcsr," in Proc. of INTERSPEECH, 2004, pp. 921-924.
15. Kris Demuynck, Jacques Duchateau, and Dirk Van Compernolle, "Optimal feature sub-space selection based on discriminant analysis," in Proc. of EUROSPEECH, 1999, pp. 1311-1314.
16. Fabio Valente, Mathew Magimai-Doss, and Wen Wang, "Analysis and comparison of recent mlp features for lvcsr systems," in Proc. of INTERSPEECH, 2011, pp. 1245-1248.
17. J. Garofolo, L. Lamel, W. Fisher, J. Fiscus, D. Pallett, and N. Dahlgren, "The DARPA TIMIT acousticphonetic continuous speech corpus cd-rom," Tech. Rep., NIST, 1993.
18. Douglas B. Paul and Janet M. Baker, "The design for the wall street journal-based csr corpus," in Proc. of the workshop on Speech and Natural Language, 1992, pp. 357-362.
19. Cheng Yang, Jean-Pierre Martens, Pol Ghesquiere, and Dirk Van Compernolle, "Pronunciation Variation Modeling for ASR: Large Improvements are possible but small ones are likely," in Proc. of ITRWon PMLA, 2002, pp. 123-128.