SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation.
Sara PapiMarco GaidoMatteo NegriLuisa BentivogliPublished in: CoRR (2024)
Keyphrases
- speech recognition
- machine translation
- speech signal
- text to speech
- speech synthesis
- audio visual
- broadcast news
- translation model
- hearing impaired
- endpoint detection
- language resources
- multimodal interfaces
- speaker verification
- speaker identification
- search engine
- automatic speech recognition
- query translation
- multi modal
- feature vectors
- pattern recognition