Target-directed mixture dynamic models for spontaneous speech recognition

  • Jeff Z. Ma, Li Deng
  • Published 2004 in IEEE Transactions on Speech and Audio Processing


In this paper, a novel mixture linear dynamic model (MLDM) for speech recognition is developed and evaluated, where several linear dynamic models are combined (mixed) to represent different vocal-tract-resonance (VTR) dynamic behaviors and the mapping relationships between the VTRs and the acoustic observations. Each linear dynamic model is formulated as… (More)
DOI: 10.1109/TSA.2003.818074

7 Figures and Tables


  • Presentations referencing similar topics