A novel bottleneck-BLSTM front-end for feature-level context modeling in conversational speech recognition

2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings

Volumn , Issue , 2011, Pages 36-41

  Wöllmer, Martin ^a   Schuller, Björn ^a   Rigoll, Gerhard ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; CONTEXT MODELING; CONVERSATIONAL SPEECH RECOGNITION; FEATURE GENERATION; FEATURE LEVEL; FEATURE VECTORS; MULTI-LAYER PERCEPTRONS; MULTI-STREAM; NETWORK TRAINING; PHONEME RECOGNITION; RECURRENT NETWORKS; SHORT TERM MEMORY; SPEECH FEATURES;

BRAIN; FEATURE EXTRACTION; PATTERN RECOGNITION SYSTEMS; SPEECH PROCESSING;

SPEECH RECOGNITION;

EID: 84858961864     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2011.6163902     Document Type: Conference Paper

References (17)

1. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. of ICASSP, Istanbul, Turkey, 2000, pp. 1635-1638.
2. F. Grezl, M. Karafiat, K. Stanislav, and J. Cernocky, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. of ICASSP, 2007.
3. M. Wöllmer, F. Eyben, B. Schuller, and G. Rigoll, "Robust vocabulary independent keyword spotting with graphical models," in Proc. of ASRU, Merano, Italy, 2009, pp. 349-353.
4. S. Thomas, S. Ganapathy, and H. Hermansky, "Phoneme recognition using spectral envelope and modulation frequency features," in Proc. of ICASSP, Taipei, Taiwan, 2009, pp. 4453-4456.
5. A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural Networks, vol. 18, no. 5-6, pp. 602-610, 2005. (Pubitemid 43186580)
6. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. (Pubitemid 127462305)
7. M. Wöllmer, F. Eyben, A. Graves, B. Schuller, and G. Rigoll, "Bidirectional LSTM networks for context-sensitive keyword detection in a cognitive virtual agent framework," Cognitive Computation, vol. 2, no. 3, pp. 180-190, 2010.
8. M. Wöllmer, F. Eyben, B. Schuller, and G. Rigoll, "Recognition of spontaneous conversational speech using long short-term memory phoneme predictions," in Proc. of Interspeech, Makuhari, Japan, 2010, pp. 1946-1949.
9. -, "A multi-stream ASR framework for BLSTM modeling of conversational speech," in Proc. of ICASSP, Prague, Czech Republic, 2011, pp. 4860-4863.
10. M. Wöllmer, B. Schuller, and G. Rigoll, "Feature frame stacking in RNN-based Tandem ASR systems - learned vs. predefined context," in Proc. of Interspeech, Florence, Italy, 2011.
11. S. Hochreiter, Y. Bengio, P. Frasconi, and J. Schmidhuber, "Gradient flow in recurrent nets: the difficulty of learning long-term dependencies," in A Field Guide to Dynamical Recurrent Neural Networks, S. C. Kremer and J. F. Kolen, Eds. IEEE Press, 2001, pp. 1-15.
12. M. Schuster and K. K. Paliwal, "Bidirectional recurrent neural networks," IEEE Transactions on Signal Processing, vol. 45, pp. 2673-2681, 1997. (Pubitemid 127766336)
13. A. Stupakov, E. Hanusa, D. Vijaywargi, D. Fox, and J. Bilmes, "The design and collection of COSINE, a multi-microphone in situ speech corpus recorded in noisy environments," Computer Speech and Language, vol. 26, no. 1, pp. 52-66, 2011.
14. M. A. Pitt, L. Dilley, K. Johnson, S. Kiesling, W. Raymond, E. Hume, and E. Fosler-Lussier, Buckeye Corpus of Conversational Speech (2nd release). Columbus, OH, USA: Department of Psychology, Ohio State University (Distributor), 2007,
15. [www.buckeyecorpus.osu.edu].
16. F. Weninger, B. Schuller, M. Wöllmer, and G. Rigoll, "Localization of non-linguistic events in spontaneous speech by non-negative matrix factorization and Long Short-Term Memory," in Proc. of ICASSP, Prague, Czech Republic, 2011, pp. 5840-5843.
17. F. Eyben, M. Wöllmer, and B. Schuller, "openSMILE - the Munich versatile and fast open-source audio feature extractor," in Proc. of ACM Multimedia, Firenze, Italy, 2010, pp. 1459-1462.