IEEE Transactions on Pattern Analysis and Machine Intelligence · 1983 · 1.2K citations · 15 references
ComputingComputer ScienceMachine LearningNatural Language ProcessingStatistical LearningLanguage ModelingLanguage ModelsMaximum Likelihood EstimationPattern RecognitionSpeech AcousticsSpeech RecognitionMaximum Likelihood InferenceMaximum-likelihood DecodingSparse Data HandlingSpeech Decoding
Speech recognition is framed as a maximum‑likelihood decoding problem that requires statistical models of speech production. The paper aims to describe statistical models for speech recognition. The authors develop statistical models, focus on parameter estimation from sparse data, and present two decoding methods—one for constrained artificial languages and another for realistic tasks—illustrated by reviewing decoding results. The methods yield promising decoding results.
Speech recognition is formulated as a problem of maximum likelihood decoding. This formulation requires statistical models of the speech production process. In this paper, we describe a number of statistical models for use in speech recognition. We give special attention to determining the parameters for such models from sparse data. We also describe two decoding methods, one appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks. To illustrate the usefulness of the methods described, we review a number of decoding results that have been obtained with them.
15
G. David Forney · Proceedings of the IEEE · 1973 · 5.7K citations
Prediction and Entropy of Printed English
Claude E. Shannon · Bell System Technical Journal · 1951 · 2.7K citations
Introduction to Theoretical Linguistics.
R. H. Robins, John Lyons · The Philosophical Quarterly · 1969 · 1.7K citations