Language Recognition on Albayzin 2010 LRE using PLLR features

• Autores: Mireia Díez Sánchez , Amparo Varona Fernández , Mikel Peñagaricano Badiola, Luis Javier Rodríguez Fuentes, Germán Bordel García
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 51, 2013, págs. 153-160
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen
  • español

    Los as´ý denominados Phone Log-Likelihood Ratios (PLLR), han sido introducidos como caracter´ýsticas alternativas a los MFCC-SDC para sistemas de Reconocimiento de la Lengua (RL) mediante iVectors. En este art´ýculo, tras una breve descripci´on de estas caracter´ýsticas, se proporcionan nuevas evidencias de su utilidad para tareas de RL, con un nuevo conjunto de experimentos sobre la base de datos Albayzin 2010 LRE, que contiene habla multi-locutor de banda ancha en seis lenguas diferentes: euskera, catal´an, gallego, espa�nol, portugu´es e ingl´es. Los sistemas de iVectors entrenados con PLLRs obtienen mejoras relativas significativas respecto a los sistemas fonot´acticos y sistemas de iVectors entrenados con caracter´ýsticas MFCC-SDC, tanto en condiciones de habla limpia como con habla ruidosa. Las fusiones de los sistemas PLLR con los sistemas fonot´acticos y/o sistemas basados en MFCC-SDC proporcionan mejoras adicionales en el rendimiento, lo que revela que las caracter´ýsticas PLLR aportan informaci´on complementaria en ambos casos

  • English

    Phone Log-Likelihood Ratios (PLLR) have been recently proposed as alternative features to MFCC-SDC for iVector Spoken Language Recognition (SLR).

    In this paper, PLLR features are first described, and then further evidence of their usefulness for SLR tasks is provided, with a new set of experiments on the Albayzin 2010 LRE dataset, which features wide-band multi speaker TV broadcast speech on six languages: Basque, Catalan, Galician, Spanish, Portuguese and English. iVector systems built using PLLR features, computed by means of three open-source phone decoders, achieved significant relative improvements with regard to the phonotactic and MFCC-SDC iVector systems in both clean and noisy speech conditions. Fusions of PLLR systems with the phonotactic and/or the MFCC-SDC iVector systems led to improved performance, revealing that PLLR features provide complementary information in both cases

• Referencias bibliográficas
  • BenZeghiba, M. F., J. L. Gauvain, and L. Lamel. September 2009. Language Score Calibration using Adapted Gaussian Back-end. In Proceedings...
  • Biadsy, Fadi, Julia Hirschberg, and Daniel P. W. Ellis. 2011. Dialect and accent recognition using phonetic-segmentation supervectors. In...
  • Brümmer, N. and J. du Preez. 2006. Application-Independent Evaluation of Speaker Detection. Computer, Speech and Language, 20(2-3):230–275.
  • Brümmer, N. and D.A. van Leeuwen. 2006. On calibration of language recognition scores. In Proceedings of Odyssey - The Speaker and Language...
  • Brümmer, Niko and Edward de Villiers. 2011. The BOSARIS Toolkit: Theory, Algorithms and Code for Surviving the New DCF. In Proceedings of...
  • Campbell, W. M., F. Richardson, and D. A. Reynolds. 2007. Language Recognition with Word Lattices and Support Vector Machines. In Proc. IEEE...
  • Dehak, N., P. Kenny, R. Dehak, P. Dumouchel, and P. Ouellet. 2011a. Front-end factor analysis for speaker verification. IEEE Transactions...
  • Dehak, N., P. A. Torres-Carrasquillo, D. A. Reynolds, and R. Dehak. 2011b. Language Recognition via i-vectors and Dimensionality Reduction....
  • DHaro, L.F., O. Glembek, O. Plocht, P. Matejka, M. Soufifar, R. Cordoba, and J. Cernocky. 2012. Phonotactic Language Recognition using i-vectors...
  • Diez, M., A. Varona, M. Penagarikano, L.J. Rodríguez Fuentes, and G.Bordel. 2012. On the Use of Phone Log-Likelihood Ratios as Features in...
  • Fan, R.E., K.W. Chang, C.J. Hsieh, X.R. Wang, and C.J. Lin. 2008. LIBLINEAR: A Library for Large Linear Classification. J. Machine Learning...
  • Martínez, D., L. Burget, L. Ferrer, and N.S. Scheffer. 2012. iVector-based Prosodic System for Language Identification. In Proceedings of...
  • Martínez, D., O. Plchot, L. Burget, O. Glembek, and P. Matejka. 2011. Language Recognition in iVectors Space. In Proceedings of Interspeech,...
  • Penagarikano, M., A. Varona, M. Diez, L.J. Rodriguez Fuentes, and G. Bordel. 2012. Study of Different Backends in a State-Ofthe-Art Language...
  • Penagarikano, M., A. Varona, L.J. Rodriguez-Fuentes, and G. Bordel. 2011. Dimensionality Reduction for Using High-Order n-grams in SVM-Based...
  • Plchot, O., M. Karafiát, N. Brümmer, O. Glembek, P. Matejka, and E. de Villiers J. Cernocký. 2012. Speaker vectors from Subspace Gaussian...
  • Rodriguez-Fuentes, L. J., M. Penagarikano, G. Bordel, and A. Varona. 2010. The Albayzin 2008 Language Recognition Evaluation. In Proceedings...
  • Rodriguez-Fuentes, L. J., M. Penagarikano, A. Varona, M. Diez, and G. Bordel. 2011. The Albayzin 2010 Language Recognition Evaluation. In...
  • Rodriguez-Fuentes, L. J., M. Penagarikano, A. Varona, M. Diez, and G. Bordel. 2012. KALAKA-2: a TV broadcast speech database for the recognition...
  • Schwarz, P. 2008. Phoneme recognition based on long temporal context. Ph.D. thesis, Faculty of Information Technology, Brno University of...
  • Singer, E., P. A. Torres-Carrasquillo, T. P. Gleason, W. M. Campbell, and D. A. Reynolds. 2003. Acoustic, Phonetic and Discriminative Approaches...
  • Soufifar, M., S. Cumani, L. Burget, and J. Cernocky. 2012. Discriminative Classifiers for Phonotactic Language Recognition with iVectors....
  • Stolcke, A. 2002. SRILM - An extensible language modeling toolkit. In Interspeech, pages 257–286.
  • Varona, Amparo, Mikel Penagarikano, Luis Javier Rodriguez Fuentes, Mireia Diez, and Germán Bordel. 2010. Verification of the four spanish...
  • Young, S., G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Lui, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland. 2006....