Title :
Recognition of demisyllable based units using semicontinuous hidden Markov models
Author :
Plannerer, B. ; Ruske, G.
Author_Institution :
Lehrstuhl fuer Datenverarbeitung, Tech. Univ. Munchen, Germany
Abstract :
The authors describe the use of semicontinuous hidden Markov models (SCHMM) for recognition of demisyllable based units within a speaker-dependent automatic recognition system for continuous speech. The processing units are demisyllables, while the decision units consist of consonant clusters and vowels. During recognition, the Viterbi algorithm is used for implicitly localizing the syllable boundaries. The estimation of the model parameters is achieved by the Viterbi training algorithm combined with a simple procedure for generating seed models. The basic principles of the algorithms are presented in detail. Application of the SCHMM approach resulted in a significantly higher performance than using discrete HMMs. The experimentally evaluated recognition rates are discussed with respect to some simplifications in the training and recognition algorithms
Keywords :
hidden Markov models; speech recognition; Viterbi training algorithm; automatic recognition system; consonant clusters; continuous speech; decision units; demisyllable based units; model parameter estimation; processing units; recognition rates; semicontinuous hidden Markov models; speaker dependent recognition; syllable boundaries; vowels; Automatic speech recognition; Clustering algorithms; Equations; Hidden Markov models; Iterative algorithms; Large Hadron Collider; Probability density function; Speech recognition; Viterbi algorithm;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.225842