Dynamic pruning for automatic speech recognition
作者： Qifeng Zhu
DOI: 10.1121/1.4820207
关键词: Pruning (decision trees) 、 Frame (networking) 、 Beam search 、 State (computer science) 、 SIGNAL (programming language) 、 Path (graph theory) 、 Computer science 、 Speech recognition
摘要: Methods, speech recognition systems, and computer readable media are provided that recognize using dynamic pruning techniques. A search network is expanded based on a frame from signal, best hypothesis determined in the network, default beam threshold modified, pruned modified threshold. The may be further depth of and/or average number frames per state for path.
harvard.edu
lens.org 参考文章(8)
Volker Steinbiss, Bach-Hiep Tran, Hermann Ney, Improvements in beam search. conference of the international speech communication association. ,(1994)
Sreeram V. Balakrishnan, Effect of task complexity on search strategies for the motorola lexicus continuous speech recognition system. conference of the international speech communication association. ,(1998)
Steve Young, Gunnar Evermann, Mark Gales, Thomas Hain, Dan Kershaw, Xunying Liu, Gareth Moore, Julian Odell, Dave Ollason, Dan Povey, Valtcho Valtchev, Phil Woodland, The HTK book Cambridge University Engineering Department and Entrophic Cambridge Research Laboratory. ,(1995)
Jean-claude Junqua, Michael Galler, Call routing device employing continuous speech ,(1996)
S. Renals, M. Hochberg, Efficient search using posterior phone probability estimates international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 596- 599 ,(1995) , 10.1109/ICASSP.1995.479668
H. Ney, S. Ortmanns, Progress in dynamic programming search for LVCSR Proceedings of the IEEE. ,vol. 88, pp. 1224- 1240 ,(2000) , 10.1109/5.880081
Bengi Karacali-Akyamac, Parameshwaran Krishnan, Mark John Karol, Adaptive parameterized search algorithm ,(2008)