@inproceedings{MachineTranslationForNSW2012,
title = {Architecture for Text Normalization using Statistical Machine Translation techniques},
author = {V. López-Ludeña and R. San-Segundo and J. M. Montero and R. Barra-Chicote and J. Lorenzo},
url = {http://consortium.simple4all.org/files/2012/04/TextNormalizationIS_v3.pdf},
year = {2012},
date = {2012-11-07},
booktitle = {Proc. Iberspeech 2012},
abstract = {This paper proposes an architecture, based on statistical machine translation, for developing the text normalization module of a text to speech conversion system. The main target is to generate a language independent text normalization module, based on data and flexible enough to deal with all situations presented in this task. The proposed architecture is composed by three main modules: a tokenizer for splitting the text input into a token graph (tokenization), a phrase-based translation module (token translation) and a post-processing module for removing some tokens. This paper presents initial experiments for numbers and abbreviations. The very good results obtained validates the proposed architecture.},
keywords = {Abbreviations, Acronyms, language translation, numbers, text normalization, text to speech conversion}
}

@inproceedings{acronyms2012,
title = {Detecting Acronyms from Capital Letter Sequences in Spanish},
author = {Ruben San-Segundo, Juan M. Montero, Veronica Lopez-Ludeña, Simon King},
url = {http://www-gth.die.upm.es/research/documentation/AG-114Det-12.pdf},
issn = {1990-9772},
year = {2012},
date = {2012-09-13},
booktitle = {Proc. Interspeech 2012},
abstract = {This paper presents an automatic strategy to decide how to pronounce a Capital Letter Sequence (CLS) in a Text to Speech system (TTS). If CLS is well known by the TTS, it can be expanded in several words. But when the CLS is unknown, the system has two alternatives: spelling it (abbreviation) or pronouncing it as a new word (acronym). In Spanish, there is a high relationship between letters and phonemes. Because of this, when a CLS is similar to other words in Spanish, there is a high tendency to pronounce it as a standard word. This paper proposes an automatic method for detecting acronyms. Additionaly, this paper analyses the discrimination capability of some features, and several strategies for combining them in order to obtain the best classifier. For the best classifier, the classification error is 8.45%. About the feature analysis, the best features have been the Letter Sequence Perplexity and the Average N-gram order.},
keywords = {Abbreviations, Acronyms, Capital letter sequence pronunciation, Spanish, Speech synthesis, Spelling}
}