Exploiting sparseness of backing-off language models for efficient look-ahead in LVCSR

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

Volumn , Issue , 2011, Pages 4684-4687

  Nolden, David ^a   Ney, Hermann ^a   Schlüter, Ralf ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

decoding; language model; look ahead; recognition; search; speech

Indexed keywords

CLASSICAL METHODS; DECODING ALGORITHM; DYNAMIC NETWORK; HIGH ORDER; LANGUAGE MODEL; LOOK-AHEAD; N-GRAM LANGUAGE MODELS; RECOGNITION; RUNTIMES; SEARCH;

DECODING; LAGRANGE MULTIPLIERS; SIGNAL PROCESSING; SPEECH COMMUNICATION;

COMPUTATIONAL LINGUISTICS;

EID: 80051606062     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947400     Document Type: Conference Paper

References (7)

1. S. Ortmanns, A. Eiden, H. Ney, and N. Coenen, "Look-ahead techniques for fast beam-search," Proc. IEEE Int. Conf. on Acoustic, Speech and Signal Processing, vol. 3, pp. 1783-1786, April 1997, Munich, Germany.
2. L. Chen and K. K. Chin, "Efficient language model look-ahead probability generation using lower order lm look-ahead information," Proc. ICASSP, 2008.
3. H. Soltau and G. Saon, "Dynamic network decoding revisited," ASRU 2009, pp. 276-281.
4. H. Ney and S. Ortmanns, "Progress in dynamic programming search for lvcsr," in Proceedings of the IEEE, Barcelona, Spain, August 2000, vol. 88, pp. 1224-1240.
5. S. Young, "A review of large-vocabulary continuousspeech recognition," IEEE Signal Processing Magazine, September 1996, pp. 45-57.
6. D. Rybach, C. Gollan, G. Heigold, B. Hoffmeister, J. Lööf, R. Schlüter, and H. Ney, "The rwth aachen university open source speech recognition system," Interspeech, September 2009, pp. 2111-2114, Brighton, U. K.
7. C. Allauzen, M. Mohri, M. Riley, and B. Roark, "A generalized construction of integrated speech recognition transducers," Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2004).