Automatic language identification using Gaussian mixture and hidden Markov models
Author:
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 399-402 vol.2
Abstract
Ergodic, continuous-observation, hidden Markov models (HMMs) were used to perform automatic language classification and detection of speech messages. State observation probability densities were modeled as tied Gaussian mixtures. The algorithm was evaluated on four multilanguage speech databases: a three language subset of the Spoken Language Library, a three language subset of a five-language Rome Laboratory database, the 20-language CCITT database, and the ten-language OGI (Oregon Graduate Institute) telephone speech database. In general, the performance of a single state HMM (i.e., a static Gaussian mixture classifier) was comparable with that of the multistate HMMs, indicating that the sequential modeling capabilities of HMMs were not exploited.Keywords
This publication has 7 references indexed in Scilit:
- RASTA-PLP speech analysis technique1992
- On the application of mixture AR hidden Markov models to text independent speaker recognitionIEEE Transactions on Signal Processing, 1991
- An automatic language identification system1991
- Automatic language recognition using acoustic features1991
- Semi-continuous hidden Markov models for speech signalsComputer Speech & Language, 1989
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- Toward automatic identification of the language of an utterance. I. Preliminary methodological considerationsThe Journal of the Acoustical Society of America, 1977