A study on continuous Chinese speech recognition based on stochastic trajectory models

查看全文 作　　者：MA Xiaohui(Department of Radio Engineering Southeast University Nanjing 210096)GONG Yifan(CRIN/CNRS France)FU Yuqing;LU Jiren(Department of Radio Engineering Southeast University Nanjing 210096) 出　　处：《Chinese Journal of Acoustics》索引1997年第16卷第4期,共6页 摘　　要：After pointed the unreasonableness of the three basic assumptions contained in HMM, we introduce the theory and the advantage of Stochastic najectory Models (STMs) that possibly resolve these problems caused by HMM assumptions. In STM, the acoustic observations of an acoustic unit are represented as clusters of trajectories in a parameter space.The trajectories are modelled by mixture of probability density functions of random sequence of states. After analyzing the characteristics of Chinese speech, the acoustic units for continuous Chinese speech recognition based on STM are discussed and phone-like units are suggested. The performance of continuous Chinese speech recognition based on STM is studied on VINICS system. The experimental results prove the efficiency of STM and the consistency of phone-like units. 关 键 词：IEEE ACTA A study on continuous Chinese speech recognition based on stochastic trajectory models