Abstract
This report describes the system used in FBK for participating in the large vocabulary Automatic Speech Recognition tasks of the Evalita 2011 evaluation campaign. The paper provides some details on the techniques included in the transcription system. The official FBK submissions were only related to the closed modality, were only data distributed within the campaign could be exploited. In this paper, results are given that were obtained with a system trained on larger corpora, thus allowing to appreciate the difference between the two modalities.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Giuliani, D., Brugnara, F.: Experiments on cross-system acoustic model adaptation. In: Proceedings of Workshop on Automatic Speech Recognition and Understanding, Kyoto, Japan, pp. 117–120 (2007)
Cettolo, M.: Segmentation, Classification and Clustering of an Italian Broadcast News Corpus. In: Proceedings of RIAO, pp. 372–381 (2000)
Young, S.J., Odell, J.J., Woodland, P.C.: Tree-based state tying for high accuracy acoustic modelling. In: Proceedings of ARPA Human Language Technology Workshop, pp. 286–291 (1994)
Giuliani, D., Gerosa, M., Brugnara, F.: Improved automatic speech recognition through speaker normalization. Computer Speech and Language 20, 107–123 (2006)
Gales, M.J.F.: Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech and Language 20, 75–98 (1998)
Gales, M.J.F.: Adaptive training for robust ASR. In: Proceedings of Workshop on Automatic Speech Recognition and Understanding, pp. 15–20 (2001)
Kumar, N., Andreou, A.G.: Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition. Speech Communication 26, 283–297 (1998)
Stemmer, G., Brugnara, F.: Integration of Heteroscedastic Linear Discriminant Analysis (HLDA) into Adapative Training. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Toulouse (2006)
Stemmer, G., Brugnara, F., Giuliani, D.: Adaptive training using simple target models. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, vol. 1, pp. 997–1000 (2005)
Ney, H., Essen, U.: On smoothing techniques for bigram-based natural language modeling. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, Toronto, Canada, pp. 825–828 (1991)
Federico, M., Bertoldi, N., Cettolo, M.: IRSTLM: an Open Source Toolkit for Handling Large Scale Language Models. In: Proceedings of Interspeech, Brisbane, Australia (2008)
Ney, H., Haeb-Umbach, R., Tran, B.-H., Oerder, M.: Improvements in beam search for 10000-word continuous speech recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, S.Francisco, CA, vol. I, pp. 9–12 (1992)
Brugnara, F., Cettolo, M.: Improvements in Tree based Language Model Representation. In: Proceedings of EUROSPEECH, Madrid, Spain, pp. 1797–1800 (1995)
Brugnara, F.: Context-dependent Search in a Context-independent Network. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, Hong Kong, vol. 1, pp. 360–363 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ronny, R., Shakoor, A., Brugnara, F., Gretter, R. (2013). The FBK ASR System for Evalita 2011. In: Magnini, B., Cutugno, F., Falcone, M., Pianta, E. (eds) Evaluation of Natural Language and Speech Tools for Italian. EVALITA 2012. Lecture Notes in Computer Science(), vol 7689. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35828-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-35828-9_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35827-2
Online ISBN: 978-3-642-35828-9
eBook Packages: Computer ScienceComputer Science (R0)