Fast Search for Large Vocabulary Speech Recognition
作者： Hermann Ney , Stephan Kanthak , Achim Sixtus , Sirko Molau , Ralf Schlüter
DOI: 10.1007/978-3-662-04230-4_5
关键词:
摘要: In this article we describe methods for improving the RWTH German speech recognizer used within Verbmobil project. particular, present acceleration search based on both within-word and across-word phoneme models. We also study incremental to reduce response time of online recognizer. Finally, experimental off-line results three scenarios. report word error rates real-time factors speaker independent dependent recognition.
springer.com
core.ac.uk
researchgate.net 
sci-hub.st 参考文章(16)
Stefan Ortmanns, Wu Chou, Wolfgang Reichl, An efficient decoding method for real time speech recognition. conference of the international speech communication association. ,(1999)
Hermann Ney, Stefan Ortmanns, Thorsten Firzlaff, Fast likelihood computation methods for continuous mixture densities in large vocabulary speech recognition. conference of the international speech communication association. ,(1997)
Peter Beyerlein, Meinhard Ullrich, Patricia Wilcox, Modelling and decoding of crossword context dependent phones in the Philips large vocabulary continuous speech recognition system. conference of the international speech communication association. ,(1997)
Roger K. Moore, Computer Speech and Language Elsevier Publishing Company. ,(1986)
S. Ortmanns, H. Ney, A. Eiden, Language-model look-ahead for large vocabulary speech recognition Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96. ,vol. 4, pp. 2095- 2098 ,(1996) , 10.1109/ICSLP.1996.607215
Xavier L. Aubert, One pass cross word decoding for large vocabularies based on a lexical tree search organization conference of the international speech communication association. pp. 1559- 1562 ,(1999)
A. Sixtus, S. Molau, S. Kanthak, R. Schluter, H. Ney, Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech international conference on acoustics, speech, and signal processing. ,vol. 3, pp. 1671- 1674 ,(2000) , 10.1109/ICASSP.2000.862071
F. Alleva, H. Hon, X. Huang, M. Hwang, R. Rosenfeld, R. Weide, Applying SPHINX-II to the DARPA Wall Street Journal CSR task Proceedings of the workshop on Speech and Natural Language - HLT '91. pp. 393- 398 ,(1992) , 10.3115/1075527.1075622
Li Lee, R.C. Rose, Speaker normalization using efficient frequency warping procedures international conference on acoustics speech and signal processing. ,vol. 1, pp. 353- 356 ,(1996) , 10.1109/ICASSP.1996.541105
K. Beulen, S. Ortmanns, C. Elting, Dynamic programming search techniques for across-word modelling in speech recognition international conference on acoustics speech and signal processing. ,vol. 2, pp. 609- 612 ,(1999) , 10.1109/ICASSP.1999.759740