Hierarchical bottle neck features for LVCSR

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 1197-1200

  Plahl, Christian ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Bottle neck; Hierarchical processing; LVCSR; Probabilistic features

Indexed keywords

DIMENSIONALITY REDUCTION; EXTRACTION; FEATURE EXTRACTION; MULTILAYER NEURAL NETWORKS; NETWORK LAYERS; SPEECH COMMUNICATION; TOPOLOGY;

BASELINE SYSTEMS; FEATURE SIZES; HIERARCHICAL PROCESSING; LVCSR; NEURAL NETWORK FEATURE EXTRACTIONS; NEURAL NETWORK TOPOLOGY; PROBABILISTIC FEATURES; SPECTRAL FEATURE; BOTTLE NECK; DIMENSIONALITY REDUCTION; FEATURES EXTRACTION; NEURAL-NETWORKS; PROBABILISTIC FEATURE; PROBABILISTICS;

BOTTLES;

EID: 79959844505     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. C. Plahl, B. Hoffmeister, G. Heigold, J. Lööf, R. Schlüter, and H. Ney, "Development of the GALE 2008 Mandarin LVCSR system," in Interspeech, Brighton, U.K., Sep. 2009, pp. 2107-2110.
2. X. Lei, W. Wu, W. Wang, A. Mandal, and A. Stolcke, "Development of the 2008 SRI Mandarin speech-to-text system for broadcast news and conversation," in Interspeech, Brighton, U.K., Sep. 2009, pp. 2099-2103.
3. F. Valente, M. Magimai-Doss, C. Plahl, S. Ravuri, and W. Wang, "A comparative large scale study of MLP features for Mandarin ASR," in Interspeech, Makuhari, Japan, Sep. 2010.
4. Q. Zhu, B. Chen, N. Morgan, and A. Stolke, "On using MLP features in LVCSR," in Interspeech, Jeju Island, Korea, Oct. 2004.
5. H. Hermansky and S. Sharma, "TRAPs - classifiers of temporal patterns," in Proc. Int. Conf. on Spoken Language Processing, Sydney, Australia, Dec. 1998.
6. H. Hermansky and P. Fousek, "Multi-resolution RASTA filtering for TANDEM-based ASR," in Interspeech, Lisbon, Portugal, Sep. 2005, pp. 361-364. (Pubitemid 43908074)
7. H. Hermansky, D. Ellis, and S. Sharma, "Tandem connectionist feature stream extraction for conventional HMM systems," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, 2000, pp. 1635-1638.
8. F. Valente, J. Vepa, C. Plahl, C. Gollan, H. Hermansky, and R. Schlüter, "Hierarchical neural networks feature extraction for LVCSR system," in Interspeech, Antwerp, Belgium, Aug. 2007, pp. 42-45.
9. F. Grézl, M. Karafiat, S. Kontar, and J. Cernock, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 4, Honolulu, HI, USA, Apr. 2007, pp. 757-760.
10. F. Grézl and P. Fousek, "Optimizing bottle-neck features for LVCSR," in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Las Vegas, NV, USA, Apr. 2008, pp. 4729-4732.
11. F. Grézl and H. Hermansky, "Local averaging and differentiating of spectral plane for TRAP-based ASR," in Interspeech, Geneva, Switzerland, Sep. 2003, pp. 1017-1020.
12. F. Valente, M. Magimai.-Doss, C. Plahl, and S. Ravuri, "Hierarchical processing of the modulation spectrum for GALE Mandarin LVCSR system," in Interspeech, Brighton, U.K., Sep. 2009, pp. 2963-2966.
13. M. Nußbaum-Thom, S. Wiesler, M. Sundermeyer, C. Plahl, S. Hahn, R. Schlüter, and H. Ney, "The RWTH 2009 QUAERO ASR evaluation system for English and German," in Interspeech, Makuhari, Japan, Sep. 2010.
14. D. Rybach, C. Gollan, G. Heigold, B. Hoffmeister, J. Lööf, R. Schlüter, and H. Ney, "The RWTH Aachen University open source speech recognition system," in Interspeech, Brighton, U.K., Sep. 2009, pp. 2111-2114.
15. C. Plahl, B. Hoffmeister, M.-Y. Hwang, D. Lu, G. Heigold, J. Lööf, R. Schlüter, and H. Ney, "Recent improvements of the RWTH GALE Mandarin LVCSR system," in Interspeech, Australia, Aug. 2008, pp. 2426-2429.
16. R. Schlüter, A. Zolnay, and H. Ney, "Feature combination using linear discriminant analysis and its pitfalls," in Interspeech, Pittsburgh, PA, USA, Sep. 2006, pp. 345-348.