Hybrid neural predictor stochastic trajectory models for Chinese speech recognition

Authors
Huang, XY Ma, XH Fu, YQ Lu, JR
Citation
Xy. Huang et al., Hybrid neural predictor stochastic trajectory models for Chinese speech recognition, ELECTR LETT, 35(10), 1999, pp. 818-820
Citations number
10
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
ELECTRONICS LETTERS
ISSN journal
00135194 → ACNP
Volume
35
Issue
10
Year of publication
1999
Pages
818 - 820
Database
ISI
SICI code
0013-5194(19990513)35:10<818:HNPSTM>2.0.ZU;2-B
Abstract
Based on stochastic trajectory models (STMs) and neural networks, a new app roach to Chinese speech recognition, the hybrid neural predictor/stochastic trajectory model (STM/NP), is proposed. STM/NP makes full use of the advan tages of STMs and the characteristics of the NN. The experimental results d emonstrate the efficiency of the STM/NP approach.