Sciweavers

60 search results - page 12 / 12
» Disambiguation of Finite-State Transducers
Sort
View
LREC
2010
159views Education» more  LREC 2010»
13 years 6 months ago
Towards Optimal TTS Corpora
Unit selection text-to-speech systems currently produce very natural synthesized phrases by concatenating speech segments from a large database. Recently, increasing demand for de...
Didier Cadic, Cédric Boidin, Christophe d'A...
FSMNLP
2005
Springer
13 years 11 months ago
German Compound Analysis with wfsc
Compounding is a very productive process in German to form complex nouns and adjectives which represent about 7% of the words of a newspaper text. Unlike English, German compounds ...
Anne Schiller
SIGIR
2003
ACM
13 years 10 months ago
Transliteration of proper names in cross-language applications
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
Paola Virga, Sanjeev Khudanpur
LREC
2008
111views Education» more  LREC 2008»
13 years 6 months ago
Low-Density Language Bootstrapping: the Case of Tajiki Persian
Low-density languages raise difficulties for standard approaches to natural language processing that depend on large online corpora. Using Persian as a case study, we propose a no...
Karine Megerdoomian, Dan Parvaz
ICASSP
2010
IEEE
13 years 5 months ago
Morphology-based and sub-word language modeling for Turkish speech recognition
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
Hasim Sak, Murat Saraclar, Tunga Güngör