Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024.
Sai KoneruThai-Binh NguyenNgoc-Quan PhamDanni LiuZhaolin LiAlexander WaibelJan NiehuesPublished in: CoRR (2024)
Keyphrases
- real time
- speech recognition
- endpoint detection
- audio visual
- speech synthesis
- speech processing
- automatic speech recognition
- query translation
- machine translation system
- spoken language
- broadcast news
- emotion recognition
- cross language information retrieval
- speaker identification
- text to speech
- recognition engine
- text to speech synthesis
- translation model
- language acquisition
- dialogue system
- speech signal
- machine translation
- face detection
- pattern recognition
- neural network
- data sets