First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

Hidden Markov Models: Past, Present, and Future

Kai-Fu Lee

School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA

Hidden Markov models (HMMs) have recently become the predominant approach to speech recognition. In this paper, we will elucidate the success of hidden Markov models, using Sphinx as an example of an HMM-based system. We will also outline avenues for future research in hidden Markov models.

Full Paper

Bibliographic reference.  Lee, Kai-Fu (1989): "Hidden Markov models: past, present, and future", In EUROSPEECH-1989, 1148-1155.