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
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;
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
