Sciweavers

ISNN
2009
Springer

Research on Segment Acoustic Model Based Mandarin LVCSR

14 years 21 days ago
Research on Segment Acoustic Model Based Mandarin LVCSR
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.
Wenju Liu, Yun Tang, Shouye Peng
Added 26 May 2010
Updated 26 May 2010
Type Conference
Year 2009
Where ISNN
Authors Wenju Liu, Yun Tang, Shouye Peng
Comments (0)