Morph-based speech recognition and modeling of out-of-vocabulary words across languages
Abstract
We explore the use of morph-based language models in large-vocabulary continuous-speech recognition systems across four so-called morphologically rich languages: Finnish, Estonian, Turkish, and Egyptian Colloquial Arabic. The morphs are subword units discovered in an unsupervised, data-driven way using the Morfessor algorithm. By estimating n -gram language models over sequences of morphs instead of words, the quality of the language model is improved through better vocabulary coverage and reduced data sparsity. Standard word models suffer from high out-of-vocabulary (OOV) rates, whereas the morph models can recognize previously unseen word forms by concatenating morphs. It is shown that the morph models do perform fairly well on OOVs without compromising the recognition accuracy on in-vocabulary words. The Arabic experiment constitutes the only exception since here the standard word model outperforms the morph model. Differences in the datasets and the amount of data are discussed as a plausible explanation.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Dec 01, 2007
- Source ID
- 10.1145/1322391.1322394
Entities
People
- Andreas Stolcke
- Antti Puurula
- Ebru Arisoy
- Janne Pylkkönen
- Mathias Creutz
- Matti Varjokallio
- Mikko Kurimo
- Murat Saraclar
- Teemu Hirsimäki
- Vesa Siivola
Organizations
- Boğaziçi University
- Defense Advanced Research Projects Agency
- Helsinki University of Technology