Robust in-car spelling recognition - A tandem BLSTM-HMM approach

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

Volumn , Issue , 2009, Pages 2507-2510

  Wöllmer, Martin ^a   Eyben, Florian ^a   Schuller, Björn ^a   Sun, Yang ^a   Moosmayr, Tobias ^b   Nguyen Thien, Nhu ^c  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b BMW GROUP   (Germany)

^c Advanced Development and Innovation ^*  (Germany)

Author keywords

Long short term memory; Noise robustness; Recurrent neural networks; Spelling recognition

Indexed keywords

DRIVING CONDITIONS; HANDS-FREE; HUMAN MACHINE INTERFACE; LOW SIGNAL-TO-NOISE RATIO; NETWORK CAPTURE; NEURAL NET; NOISE ROBUSTNESS; SHORT TERM MEMORY; SPEECH RECOGNITION ENGINE; SPEECH SEQUENCES; SPEECH SIGNALS; TEST NOISE;

ACOUSTIC NOISE; BRAIN; HIDDEN MARKOV MODELS; SIGNAL TO NOISE RATIO; SPEECH COMMUNICATION; SPEECH RECOGNITION;

RECURRENT NEURAL NETWORKS;

EID: 70450180507     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. C. D. Mitchell and A. R. Setlur, "Improving spelling recognition using a tree-based fast lexical match," in Proc. of ICASSP, vol. 2, Phoenix, AZ, USA, 2008, pp. 597-600.
2. B. Schuller, M. Wöllmer, T. Moosmayr, and G. Rigoll, "Recognition of noisy speech: A comparative survey of robust model architectures and feature enhancement," Journal on Audio, Speech, and Music Processing (to appear), 2009, id 942617.
3. J. Droppo and A. Acero, "Noise robust speech recognition with a switching linear dynamic model," in Proc. of ICASSP, Montreal, Canada, 2004.
4. B. Schuller, M. Wöllmer, T. Moosmayr, and G. Rigoll, "Speech recognition in noisy environments using a switching linear dynamic model for feature enhancement," in Proc. of Interspeech, Brisbane, Australia, 2008, pp. 1789-1792.
5. H. Ketabdar and H. Bourlard, "Enhanced phone posteriors for improving speech recognition systems," in IDIAP-RR, no. 39, 2008.
6. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional hmm systems," in Proc. of ICASSP, vol. 3, Istanbul, Turkey, 2000, pp. 1635-1638.
7. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9(8), pp. 1735-1780, 1997.
8. M. Schuster and K. K. Paliwal, "Bidirectional recurrent neural networks," IEEE Transactions on Signal Processing, vol. 45, pp. 2673-2681, 1997.
9. A. Graves, S. Fernandez, and J. Schmidhuber, "Bidirectional lstm networks for improved phoneme classification and recognition," in Proc. of ICANN, Warsaw, Poland, 2005, pp. 602-610.
10. M. Wöllmer, F. Eyben, J. Keshet, A. Graves, B. Schuller, and G. Rigoll, "Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks," in Proc. of ICASSP, Taipei, Taiwan, 2009.
11. M. Wöllmer, F. Eyben, S. Reiter, B. Schuller, C. Cox, E. Douglas-Cowie, and R. Cowie, "Abandoning emotion classes - towards continuous emotion recognition with modelling of long-range dependencies," in Proc. of Interspeech, Brisbane, Australia, 2008, pp. 597-600.
12. A. Graves, "Supervised sequence labelling with recurrent neural networks," Ph.D. dissertation, Technische Universität München, 2008.
13. J. A. Bilmes and C. Bartels, "Graphical model architectures for speech recognition," IEEE Signal Processing Magazine, vol. 22, no. 5, pp. 89-100, 2005.