In Interspeech 2007. Proceedings of the 8th Annual Conference of the International Speech Communication Association, pages 2137-2140. Antwerp, Belgium, August 27-31, 2007.
![Language identification using several sources of information with a multiple-Gaussian classifier [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex We present several innovative techniques that can be applied in a PPRLM system for language identification (LID). To normalize the scores, eliminate the bias in the scores and improve the classifier, we compared the bias removal technique (up to 19% relative improvement (RI)) and a Gaussian classifier (up to 37% RI). Then, we include additional sources of information in different feature vectors of the Gaussian classifier: the sentence acoustic score (11% RI), the average acoustic score for each phoneme (11% RI), and the average duration for each phoneme (7.8% RI). The use of a multiple-Gaussian classifier with 4 feature vectors meant an additional 15.1% RI. Using 4 feature vectors instead of just PPRLM provides a 26.1% RI. Finally, we include additional acoustic HMMs of the same language with success (10% relative improvement). We will show how all these improvements have been mostly additive.
@incollection{de_cordoba_language_2007-1,
Author = {de Córdoba, Ricardo and D'Haro, Luis Fernando and Fernández Martínez, Fernando and Montero, Juan Manuel and Barra, Roberto},
Booktitle = {Interspeech 2007. Proceedings of the 8th Annual Conference of the International Speech Communication Association},
Date = {2007},
Date-Modified = {2016-09-24 18:56:01 +0000},
Keywords = {language identification, Spanish, speech technology},
Pages = {2137-2140},
Publisher = {Antwerp, Belgium, August 27-31, 2007},
Title = {Language identification using several sources of information with a multiple-Gaussian classifier},
Url = {http://www-gth.die.upm.es/research/documentation/AG-057Lan-07.pdf},
Abstract = {We present several innovative techniques that can be applied in a PPRLM system for language identification (LID). To normalize the scores, eliminate the bias in the scores and improve the classifier, we compared the bias removal technique (up to 19\% relative improvement (RI)) and a Gaussian classifier (up to 37\% RI). Then, we include additional sources of information in different feature vectors of the Gaussian classifier: the sentence acoustic score (11\% RI), the average acoustic score for each phoneme (11\% RI), and the average duration for each phoneme (7.8\% RI). The use of a multiple-Gaussian classifier with 4 feature vectors meant an additional 15.1\% RI. Using 4 feature vectors instead of just PPRLM provides a 26.1\% RI. Finally, we include additional acoustic HMMs of the same language with success (10\% relative improvement). We will show how all these improvements have been mostly additive.},
Bdsk-File-1 = {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},
Bdsk-Url-1 = {http://www-gth.die.upm.es/research/documentation/AG-057Lan-07.pdf}}Downloads: 0