Generating word hypotheses in continuous speech
暂无分享,去创建一个
This paper addresses the problem of generating word hypotheses in continuous German speech. It uses an extension of the well-known hidden Markow models in order to model more accurately the properties of the phonetic labeling stage. A powerful scoring function is derived. Experimental results are presented which were computed speaker independently.
[1] P. Regel,et al. A module for acoustic-phonetic transcription of fluently spoken German speech , 1982 .
[2] Masafumi Nishimura,et al. Isolated word recognition using hidden Markov models , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.
[3] Michael D. Brown,et al. An algorithm for connected word recognition , 1982, ICASSP.
[4] Lalit R. Bahl,et al. A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.