论文信息 - An unsupervised approach to language identification

An unsupervised approach to language identification

This paper presents an unsupervised approach to automatic language identification (ALI) based on vowel system modeling. Each language vowel system is modeled by a Gaussian mixture model (GMM) trained with automatically detected vowels. Since this detection is unsupervised and language independent, no labeled data are required. GMMs are initialized using an efficient data-driven variant of the LBG algorithm: the LBG-Rissanen (1983) algorithm. With 5 languages from the OGI MLTS corpus and in a close set identification task, we reach 79% of correct identification using only the vowel segments detected in 45 second duration utterances for the male speakers.

François Pellegrino | Régine André-Obrecht

[1] Régine André-Obrecht,et al. A new statistical approach for the automatic segmentation of continuous speech signals , 1988, IEEE Trans. Acoust. Speech Signal Process..

[2] Jean-François Bonastre,et al. Subband Approach for Automatic Speaker Recognition: Optimal Division of the Frequency Domain , 1997, AVBPA.

[3] Christian Abry,et al. Major trends in vowel system inventories , 1997 .

[4] Steven J. Nowlan,et al. Soft competitive adaptation: neural network learning algorithms based on fitting statistical mixtures , 1991 .

[5] Robert M. Gray,et al. An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[6] J. Rissanen. A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[7] Marc A. Zissman,et al. Comparison of : Four Approaches to Automatic Language Identification of Telephone Speech , 2004 .

[8] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[9] François Pellegrino,et al. From vocalic detection to automatic emergence of vowel systems , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.