DocumentCode
1643265
Title
Language recognition by means of ergodic hidden Markov models
Author
du Preez, J.A.
Author_Institution
Dept. of Electr. & Electron. Eng., Stellenbosch Univ., South Africa
fYear
1992
fDate
9/11/1992 12:00:00 AM
Firstpage
39
Lastpage
42
Abstract
This model, which can be trained without user intervention, in addition to modelling the sounds present in a specific language, attempts to capture the typical combinations of sounds specific to that language. It is shown how this model can be extended to include a wider context than that offered by a first order HMM without incurring the excessive computational burden of higher order Markov models
Keywords
computational complexity; hidden Markov models; natural languages; speech recognition; combinations of sounds; computational burden; ergodic hidden Markov models; language recognition; Acoustic noise; Acoustical engineering; Context modeling; Databases; Frequency locked loops; Hidden Markov models; Probability density function; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications and Signal Processing, 1992. COMSIG '92., Proceedings of the 1992 South African Symposium on
Conference_Location
Cape Town
Print_ISBN
0-7803-0807-7
Type
conf
DOI
10.1109/COMSIG.1992.274316
Filename
274316
Link To Document