Fact · Speech recognition
Rabiner's 1989 tutorial says HMMs must solve three fundamental problems before they apply to speech: evaluating the likelihood of an observation sequence, finding the best sequence of model states, and adjusting model parameters to fit the observed signal.
Checked against its source on October 17, 2026
In the source's own words
“evaluation of the probability (or likelihood) of a sequence of observations given a specific HMM; the determination of a best sequence of model states; and the adjustment of model parameters so as to best account for the observed signal”
A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Lawrence R. Rabiner, Proceedings of the IEEE, vol. 77, no. 2, pp. 257-286, 1989, Introduction.
Open the original (DOI 10.1109/5.18626)- What it measures
- The tutorial is the standard reference for the HMM systems that dominated speech recognition for decades.
- What it does not show
- The three problems are the theory. Real recognizers added many engineering steps on top, such as pronunciation dictionaries and language models.
Source
Cited on
- How Speech Recognition Works, From Sound to TextGuide
- History of Speech Recognition: From Audrey to WhisperGuide
- Is speech recognition AI?Question
- What are the most important speech recognition research papers?Question
- What role do hidden Markov models play in speech recognition?Question
- Hidden Markov model (HMM)Glossary