Investigation into bottle-neck features for meeting speech recognition

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

Volumn , Issue , 2009, Pages 2947-2950

  Grézl, František ^a   Karafíat, Martin ^a   Burget, Lukáš ^a  

^a BRNO UNIVERSITY OF TECHNOLOGY   (Czech Republic)

Author keywords

ANN architecture; Bottle neck; Features; LVCSR

Indexed keywords

ANN ARCHITECTURE; CONTEXT ARCHITECTURE; DISCRIMINATIVE FEATURE EXTRACTION; MODEL PARAMETERS;

BACKPROPAGATION; BOTTLES; SPEECH COMMUNICATION; SPEECH RECOGNITION;

FEATURE EXTRACTION;

EID: 70450211380     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. ICASSP 2000, Turkey, 2000.
2. H. Hermansky and S. Sharma, "TRAPs - classifiers of temporal patterns," in 5th International Conference on Spoken Language Processing (ICSLP), Sydney, Nov 1998.
3. F. Grézl and H. Hermansky, "Local averaging and differentiating of spectral plane for TRAP-based ASR," in Proc. Eurospeech 2003, Geneva, Switzerland, 2003.
4. B. Chen, Q. Zhu, and N. Morgan, "Tonotopic multi-layered perceptron: A neural network for learning long-term temporal features for speech recognition," in Proc. ICASSP 2005, Philadelphia, PA, USA, Mar. 2005.
5. P. Schwarz, P. Matějka, and J. Černocký, "Towards lower error rates in phoneme recognition," in Proceedings of 7th International Conference Text, Speech and Dialogue 2004, 2004, p. 8.
6. A. Janin, A. Stolcke, X. Anguera, K. Boakye, O. Cetin, J. Frankel, and J. Zheng, "The ICSI-SRI Spring 2006 meeting recognition system," in 3nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, May 2006.
7. T. Hain et al., "The AMI system for the transcription of speech meetings," in Proc. ICASSP 2007, Honolulu, Hawaii, USA, Apr 2007, pp. 357-360.
8. F. Grézl, M. Karafíat, S. Kontár, and J. Černocký, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. ICASSP 2007, Honolulu, Hawaii, USA, Apr 2007, pp. 757-760.
9. F. Grézl and P. Fousek, "Optimizing bottle-neck features for LVCSR," in 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2008, pp. 4729-4732.
10. B. Chen, Q. Zhu, and N. Morgan, "Learning long-term temporal features in LVCSR using neural networks," in Proc. ICSLP 2004, Jeju Island, KR, Oct. 2004.
11. P. Schwarz, P. Matějka, and J. Černocký, "Hierarchical structures of neural networks for phoneme recognition," in ICASSP, Toulouse, France, may 2006.
12. D. Povey, "Discriminative training for large vocabulary speech recognitionk," Ph.D. dissertation, Cambridge University Engineering Department, Mar. 2003.
13. D. Povey, "Improvements to fMPE for discriminative training of features," in Proc. of Interspeech2005, Lisbon, Portugal, Sep 2005, pp. 2977-2980.
14. B. Zhang, S. Matsoukas, and R. Schwartz, "Recent progress on the discriminative region-dependent transform for speech feature extraction," in Proc. of Interspeech2006, Pittsburgh, PA, USA, Sep 2006, pp. 2977-298