Bell System Technical Journal · 1983 · 984 citations · 23 references
Isolated WordEngineeringSpoken Language ProcessingSpeech RecognitionHidden Markov ModelComputational LinguisticsProbabilistic FunctionsRobust Speech RecognitionVoice RecognitionMarkov ProcessMarkov ChainHealth SciencesProbability TheoryComputer ScienceSpeech SignalSignal ProcessingSpeech CommunicationAutomatic Speech RecognitionSpeech AcousticsMarkov KernelSpeech ProcessingSpeech InputSpeech PerceptionLinguistics
Left‑to‑right Markov models are especially suitable for isolated word recognition. This paper presents key theoretical and practical issues in modeling speech signals as probabilistic functions of hidden Markov chains. We review the literature with emphasis on the Baum‑Welch algorithm, discuss alternatives, implementation details, and behavior on realistic problems, and focus on left‑to‑right models. Results of applying these methods to an isolated word, speaker‑independent speech recognition experiment are reported in a companion paper.
In this paper we present several of the salient theoretical and practical issues associated with modeling a speech signal as a probabilistic function of a (hidden) Markov chain. First we give a concise review of the literature with emphasis on the Baum-Welch algorithm. This is followed by a detailed discussion of three issues not treated in the literature: alternatives to the Baum-Welch algorithm; critical facets of the implementation of the algorithms, with emphasis on their numerical properties; and behavior of Markov models on certain artificial but realistic problems. Special attention is given to a particular class of Markov models, which we call “left-to-right” models. This class of models is especially appropriate for isolated word recognition. The results of the application of these methods to an isolated word, speaker-independent speech recognition experiment are given in a companion paper.
23