DocumentCode
3406947
Title
Efficient Viterbi beam search algorithm using dynamic pruning
Author
Lingyun, Xie ; Limin, Du
Author_Institution
Labs for Speech Interaction Technol. Res., Chinese Acad. of Sci., Beijing, China
Volume
1
fYear
2004
fDate
31 Aug.-4 Sept. 2004
Firstpage
699
Abstract
The efficiency of search algorithm is the key problem of large vocabulary continuous speech recognition (LVCSR) systems. This paper explores this issue and presents a dynamic pruning method based on Viterbi beam search algorithm. At each time frame, the proposed method can adjust the beam widths based on the current situation of search process. The experimental results show that it can reduce the computation complexity without degrading the recognition rate much. It is advantageous for implementations on real-time systems.
Keywords
computational complexity; search problems; speech recognition; vocabulary; Viterbi beam search algorithm; beam width; dynamic pruning; large vocabulary continuous speech recognition system; Acoustic beams; Computational efficiency; Degradation; Heuristic algorithms; Molecular beam epitaxial growth; Real time systems; Speech recognition; Upper bound; Viterbi algorithm; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN
0-7803-8406-7
Type
conf
DOI
10.1109/ICOSP.2004.1452759
Filename
1452759
Link To Document