mintzai-ST: Corpus and Baselines for Basque-Spanish Speech Translation.
Thierry EtchegoyhenHaritz ArzelusHarritxu Gete UgarteAitor ÁlvarezAnder González-DocasalEdson Benites FernandezPublished in: IberSPEECH (2021)
Keyphrases
- machine translation system
- language identification
- spanish language
- speaker identification
- language resources
- statistical machine translation
- machine translation
- broadcast news
- spontaneous speech
- parallel corpora
- pronominal anaphora
- speech signal
- speech recognition
- conversational speech
- query translation
- mono lingual
- parallel corpus
- automatic speech recognition
- cross language information retrieval
- cross lingual
- lexical features
- english words
- audio visual
- sentence pairs
- speech processing
- speech synthesis
- spoken language
- document level
- comparable corpora
- chinese english
- question answering
- word alignment
- document images
- translation model
- target language
- cross language retrieval
- sentence level
- gaussian mixture model
- language model
- hearing impaired
- co occurrence