Paper Info
Title
Research on Segment Acoustic Model Based Mandarin LVCSR
Abstract
SM has shown a better performance than HMM in connected word recognition system; however, no reports we have read show that SM has been applied in LVCSR as decoding acoustic model because of the restriction of its complexity. We have preliminarily built a SM based mandarin LVCSR system which adopts CART and global tying to tie the parameters in the triphone models and the fast SM algorithm, CF algorithm and two-level pruning to enhance the speed of decoding. The system achieves 87.09% syllable accuracy in Test-863 data corpus within 4 real times. We believe SM offers an alternative choice for LVCSR system though further research for its fast algorithms by rational utilization of its structure information.
Year
DOI
Venue
2009
10.1007/978-3-642-01510-6_105
ISNN (2)
Keywords
Field
DocType
fast sm algorithm,segment acoustic model,test-863 data corpus,connected word recognition system,mandarin lvcsr system,mandarin lvcsr,fast algorithm,alternative choice,lvcsr system,better performance,acoustic model,cf algorithm,word recognition,hmm,real time
Triphone,Pattern recognition,Computer science,Word recognition,Speech recognition,Syllable,Artificial intelligence,Decoding methods,Hidden Markov model,Mandarin Chinese,Acoustic model
Conference
Volume
ISSN
Citations 
5552
0302-9743
0
PageRank 
References 
Authors
0.34
3
3
Name
Order
Citations
PageRank
Wenju Liu121439.32
Yun Tang272.73
Shouye Peng351.52