AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation.
Sara PapiMarco TurchiMatteo NegriPublished in: INTERSPEECH (2023)
Keyphrases
- machine translation
- cross language information retrieval
- multimedia
- query translation
- broadcast news
- audio visual
- speaker identification
- statistical machine translation
- cepstral features
- information retrieval
- language resources
- audio signals
- machine translation system
- emotion recognition
- target language
- cross language
- human computer interaction
- signal processing