Abstract | ||
---|---|---|
In this paper, a language identification system is described that implements the Fishervoice approach in order to reduce the dimensionality of the data. Fishervoice performs two-dimensional Principal Component Analysis (2D-PCA) and Linear Discriminant Analysis (LDA) to project the data into a discriminative subspace. After this transformation the speech utterances are transformed into supervectors and classified by means of a Support Vector Machine (SVM). Experiments performed on KALAKA-2 database, which includes speech in Spanish, Catalan, English, Basque, Galician and Portuguese, show that the Fishervoice-SVM system achieves good identification results while reducing dramatically the number of features needed to represent the speech utterances. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-28885-2_43 | PROPOR |
Keywords | Field | DocType |
linear discriminant analysis,support vector machine,language identification system,discriminative subspace,speech utterance,fishervoice approach,component analysis,fishervoice-svm language identification system,fishervoice-svm system,good identification result,kalaka-2 database,support vector machines,language identification | Catalan,Pattern recognition,Subspace topology,Computer science,Support vector machine,Curse of dimensionality,Speech recognition,Language identification,Artificial intelligence,Linear discriminant analysis,Discriminative model,Principal component analysis | Conference |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paula Lopez-Otero | 1 | 64 | 13.18 |
Laura Docio-Fernandez | 2 | 20 | 4.00 |
Carmen Garcia-Mateo | 3 | 96 | 4.48 |