Experiments for the Selection of Sub-Word Units in the Basque Context

The development of Multilingual Automatic Speech Recognition (ASR) systems involves Acoustic Phonetic Decoding, Language Modeling, Language Identification and the development of appropriated Language Resources. Only a small number of languages possess the resources required for these developments, the remaining languages are under-resourced. In this paper we explore robust strategies of Soft Computing in the selection of sub-word units oriented to under-resourced languages for ASR in the Basque context. Three languages are analyzed: French, Spanish and the minority one, Basque language. The proposed methodology is based on approaches of Discriminant and Principal Components Analysis, robust covariance matrix estimation methods, Support Vector Machines (SVM), Hidden Markov Models (HMMs) and cross-lingual strategies. New methods improve considerably the accuracy rate obtained on incomplete, small sample sets, providing an excellent tool to manage these kinds of languages.

[1]  Antonio Moreno-Sandoval,et al.  Acoustic-phonetic decoding of different types of spontaneous speech in Spanish , 2005, DiSS.

[2]  Piero Cosi.  Hybrid HMM-NN architectures for connected digit recognition , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[3]  Alberto Sanfeliu,et al.  Progress in Pattern Recognition, Speech and Image Analysis , 2003, Lecture Notes in Computer Science.

[4]  Aaron E. Rosenberg,et al.  Improved acoustic modeling for speaker independent large vocabulary continuous speech recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[5]  Joseph Picone,et al.  Hybrid SVM/HMM architectures for speech recognition , 2000, INTERSPEECH.

[6]  Mark J. F. Gales,et al.  Speech Recognition using SVMs , 2001, NIPS.

[7]  Laurent Besacier,et al.  Which units for acoustic and language modeling for Khmer automatic speech recognition? , 2008, SLTU.

[8]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Kazuhiro Kondo,et al.  An evaluation of cross-language adaptation for rapid HMM development in a new language , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  David A. Landgrebe,et al.  Covariance Matrix Estimation and Classification With Limited Training Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Tanja Schultz,et al.  Multilingual Speech Processing , 2006 .

[12]  Karmele López de Ipiña,et al.  Development of multimodal resources for multilingual information retrieval in the basque context , 2007, INTERSPEECH.

[13]  João Paulo da Silva Neto,et al.  The COST278 Pan-European Broadcast News Database , 2004, LREC.

[14]  J. Friedman.  Regularized Discriminant Analysis , 1989 .

[15]  Saldju Tadjudin,et al.  CLASSIFICATION OF HIGH DIMENSIONAL DATA WITH LIMITED TRAINING SAMPLES , 1998 .

[16]  Manuel Graña,et al.  Selection of Lexical Units for Continuous Speech Recognition of Basque , 2003, CIARP.

[17]  David A. Landgrebe,et al.  Covariance estimation with limited training samples , 1999, IEEE Trans. Geosci. Remote. Sens..

[18]  Fernando Díaz-de-María,et al.  Support Vector Machines for continuous speech recognition , 2006, 2006 14th European Signal Processing Conference.

[19]  Tanja Schultz,et al.  Multilingual and Crosslingual Speech Recognition , 1998 .

[20]  Laurent Besacier,et al.  Automatic Speech Recognition for Under-Resourced Languages: Application to Vietnamese Language , 2009, IEEE Transactions on Audio, Speech, and Language Processing.