M. Inés Torres

Also published as: María Inés Torres


2014

pdf
Basque Speecon-like and Basque SpeechDat MDB-600: speech databases for the development of ASR technology for Basque
Igor Odriozola | Inma Hernaez | María Inés Torres | Luis Javier Rodriguez-Fuentes | Mikel Penagarikano | Eva Navas
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

This paper introduces two databases specifically designed for the development of ASR technology for the Basque language: the Basque Speecon-like database and the Basque SpeechDat MDB-600 database. The former was recorded in an office environment according to the Speecon specifications, whereas the later was recorded through mobile telephones according to the SpeechDat specifications. Both databases were created under an initiative that the Basque Government started in 2005, a program called ADITU, which aimed at developing speech technologies for Basque. The databases belong to the Basque Government. A comprehensive description of both databases is provided in this work, highlighting the differences with regard to their corresponding standard specifications. The paper also presents several initial experimental results for both databases with the purpose of validating their usefulness for the development of speech recognition technology. Several applications already developed with the Basque Speecon-like database are also described. Authors aim to make these databases widely known to the community as well, and foster their use by other groups.

2013

pdf bib
Stochastic Bi-Languages to model Dialogs
M. Inés Torres
Proceedings of the 11th International Conference on Finite State Methods and Natural Language Processing

2012

pdf
Finite-State Acoustic and Translation Model Composition in Statistical Speech Translation: Empirical Assessment
Alicia Pérez | M. Inés Torres | Francisco Casacuberta
Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing

2011

pdf
Stochastic K-TSS Bi-Languages for Machine Translation
M. Inés Torres | Francisco Casacuberta
Proceedings of the 9th International Workshop on Finite State Methods and Natural Language Processing

2010

pdf
Potential scope of a fully-integrated architecture for speech translation
Alicia Pérez | María Inés Torres | Francisco Casacuberta
Proceedings of the 14th Annual conference of the European Association for Machine Translation

2007

pdf bib
A comparison of linguistically and statistically enhanced models for speech-to-speech machine translation
Alicia Pérez | Víctor Guijarrubia | Raquel Justo | M. Inés Torres | Francisco Casacuberta
Proceedings of the Fourth International Workshop on Spoken Language Translation

The goal of this work is to improve current translation models by taking into account additional knowledge sources such as semantically motivated segmentation or statistical categorization. Specifically, two different approaches are discussed. On the one hand, phrase-based approach, and on the other hand, categorization. For both approaches, both statistical and linguistic alternatives are explored. As for translation framework, finite-state transducers are considered. These are versatile models that can be easily integrated on-the-fly with acoustic models for speech translation purposes. In what the experimental framework concerns, all the models presented were evaluated and compared taking confidence intervals into account.

pdf
Speech-Input Multi-Target Machine Translation
Alicia Pérez | M. Teresa González | M. Inés Torres | Francisco Casacuberta
Proceedings of the Second Workshop on Statistical Machine Translation

pdf
An Integrated Architecture for Speech-Input Multi-Target Machine Translation
Alicia Pérez | M. Teresa González | M. Inés Torres | Francisco Casacuberta
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers