Comparison and combination of different CRBE based MLP features for LVCSR

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2012, Pages 4081-4084

  Tüske, Zoltán ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

CRBE; Dempster Shafer; GT; LVCSR; MFCC; MRASTA; PLP

Indexed keywords

CRBE; DEMPSTER-SHAFER; GT; LVCSR; MFCC; MRASTA; PLP;

SIGNAL PROCESSING;

SPEECH RECOGNITION;

EID: 84867610342     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288815     Document Type: Conference Paper

References (15)

1. F. Valente et al., "Analysis and Comparison of Recent MLP Features for LVCSR Systems," in Proc. of Interspeech, 2011, pp. 1245-1248.
2. C. Plahl et al., "Improved Acoustic Feature Combination for LVCSR by Neural Networks," in Proc. of Interspeech, 2011, pp. 1237-1240.
3. H. Hermansky and P. Fousek, "Multi-resolution RASTA filtering for TANDEM-based ASR," in Proc. of Interspeech, 2005, pp. 361-364.
4. B. Chen et al., "Learning long-term temporal features in LVCSR using neural networks," in Proc. of Int. Conf. on Spoken Language Processing, 2004, pp. 612-615.
5. F. Grézl and M. Karafiát, "Hierarchical Neural Net Architectures for Feature Extraction in ASR," in Interspeech, 2010, pp. 1201-1204.
6. J. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (rover)," in Proc. of IEEE Automatic Speech Recognition and Understanding Workshop, 1997, pp. 347-354.
7. R. Schlüter et al., "Gammatone features and feature combination for large vocabulary speech recognition," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2007, pp. 649-652.
8. F. Valente, "Multi-stream speech recognition based on Dempster-Shafer combination rule," Speech Communication, vol. 52, no. 3, pp. 213-222, Mar. 2010.
9. Z. Tüske et al., "A study on speaker normalized MLP features in LVCSR," in Proc. of Intererspeech, 2011, pp. 1089-1092.
10. S. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 28, no. 4, pp. 357-366, Aug. 1980.
11. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," Journal of the Acoustical Society of America, vol. 87, no. 4, pp. 1738-1752, 1990.
12. F. Valente and H. Hermansky, "Hierarchical and parallel processing of modulation spectrum for ASR applications," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2008, pp. 4165-4168.
13. H. Hermansky et al., "Tandem connectionist feature extraction for conventional HMM systems," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 3, 2000, pp. 1635-1638.
14. M. Sundermeyer et al., "The RWTH 2010 QUAERO ASR Evaluation System for English, French, and German," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2011, pp. 2212-2215.
15. G. Stemmer et al., "Adaptive training using simple target models," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 1, 2005, pp. 997-1000.