Chapter

Advances in Speech and Language Technologies for Iberian Languages

Volume 8854 of the series Lecture Notes in Computer Science pp 79-88

On the Use of Convolutional Neural Networks in Pairwise Language Recognition

  • Alicia Lozano-DiezAffiliated withATVS - Biometric Recognition Group, Universidad Autonoma de Madrid (UAM)
  • , Javier Gonzalez-DominguezAffiliated withATVS - Biometric Recognition Group, Universidad Autonoma de Madrid (UAM)
  • , Ruben ZazoAffiliated withATVS - Biometric Recognition Group, Universidad Autonoma de Madrid (UAM)
  • , Daniel RamosAffiliated withATVS - Biometric Recognition Group, Universidad Autonoma de Madrid (UAM)
  • , Joaquin Gonzalez-RodriguezAffiliated withATVS - Biometric Recognition Group, Universidad Autonoma de Madrid (UAM)

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Convolutional deep neural networks (CDNNs) have been successfully applied to different tasks within the machine learning field, and, in particular, to speech, speaker and language recognition. In this work, we have applied them to pair-wise language recognition tasks. The proposed systems have been evaluated on challenging pairs of languages from NIST LRE’09 dataset. Results have been compared with two spectral systems based on Factor Analysis and Total Variability (i-vector) strategies, respectively. Moreover, a simple fusion of the developed approaches and the reference systems has been performed. Some individual and fusion systems outperform the reference systems, obtaining ~ 17% of relative improvement in terms of minC DET for one of the challenging pairs.

Keywords

Convolutional networks CDNNs pair-wise language recognition