First International Conference on Spoken Language Processing (ICSLP 90)
Natural languages were modeled popularly by Markov models. In this paper, natural languages were modeled by HMM (Hidden Markov Model). And the identification of language and the prediction for phoneme/syllable/word-category were performed using HMM. The results show that the HMM had a performance better than the first order Markov model (bigram) and almost the same as the second order Markov model (trigram) on the entropy. From the results, we believe that HMM is not useful only speech recognition but also natural language processing.
Bibliographic reference. Ueda, Yoshio / Nakagawa, Seiichi (1990): "Diction for phoneme/syllable/word-category and identification of language using HMM", In ICSLP-1990, 1209-1212.