DocumentCode
1933828
Title
Application of GMM models to spoken language recognition
Author
Dustor, Adam ; Szwarc, Pawel
Author_Institution
Inst. of Electron., Silesian Univ. of Technol., Gliwice, Poland
fYear
2009
fDate
25-27 June 2009
Firstpage
603
Lastpage
606
Abstract
This paper presents research on automatic spoken language recognition based on statistical pattern recognition. As a model of identified language Gaussian mixture model was applied, both with diagonal and full covariance matrix. The influence of GMM order and parameterizations of speech signal on the recognition results were examined. Tests were done for 10 languages. Obtained results were discussed.
Keywords
Gaussian processes; covariance matrices; natural languages; speech recognition; statistical analysis; GMM model; Gaussian mixture model; automatic spoken language recognition; diagonal covariance matrix; full covariance matrix; speech signal recognition; statistical pattern recognition; Application specific integrated circuits; Covariance matrix; Integrated circuit modeling; Integrated circuit technology; Mathematical model; Multidimensional systems; Natural languages; Pattern recognition; Speech recognition; Vectors; GMM; pattern recognition; speech; spoken language recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Mixed Design of Integrated Circuits & Systems, 2009. MIXDES '09. MIXDES-16th International Conference
Conference_Location
Lodz
Print_ISBN
978-1-4244-4798-5
Electronic_ISBN
978-83-928756-1-1
Type
conf
Filename
5289511
Link To Document