Bilingual aligned corpora for speech to speech translation for Spanish, English and Catalan.
David ConejeroAlan LoundsCarmen García-MateoLeandro Rodríguez LiñaresRaquel MochalesAsunción MorenoPublished in: INTERSPEECH (2005)
Keyphrases
- machine translation
- machine translation system
- chinese english
- parallel corpus
- statistical machine translation
- parallel corpora
- cross language information retrieval
- broadcast news
- comparable corpora
- query translation
- text to speech
- language resources
- sentence pairs
- phrase based smt
- cross language
- english text
- speech recognition
- finite state transducers
- cross lingual
- out of vocabulary
- parallel texts
- word alignment
- bilingual dictionaries
- natural language processing
- automatic speech recognition
- spoken language
- spoken document retrieval
- cross language retrieval
- english chinese
- machine readable dictionaries
- translation model
- question answering
- linguistic resources
- language identification
- speaker identification
- target language
- speech signal
- language model
- source language
- dialogue system
- audio visual
- pronominal anaphora
- natural language
- training corpus
- multiword
- labor intensive
- lexical knowledge
- monolingual retrieval
- mono lingual
- wordnet