ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Connected spoken word recognition using a many-state Markov model

Tomio Takara, Naoto Matayoshi, Kazuya Higa

This paper is a report on an application of the Markov model to an automatic speech recognition system, in which a large number of states are adopted to model the transitional characteristics of speech more accurately. Unlike the traditional HMM, the feature vectors of this model are regarded to be the states of the Markov model. The transition-probability of the state is, in its initial condition, assumed to be represented by multidimensional normal density function of the feature vector. The many-state model is obtained by quantizing the feature vector (state) space and sampling the probability density function at each code vector. The resulting recognizer was tested and compared on a vocabulary of four-digit numerals using 3 dimensional feature vector sequences. The many-state model attained a recognition score of 98.2%, which was 1.6% higher than that of a five-state traditional HMM.


Cite as: Takara, T., Matayoshi, N., Higa, K. (1994) Connected spoken word recognition using a many-state Markov model. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 235-238

@inproceedings{takara94_icslp,
  author={Tomio Takara and Naoto Matayoshi and Kazuya Higa},
  title={{Connected spoken word recognition using a many-state Markov model}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={235--238}
}