Contextualized Translation of Automatically Segmented Speech.
Marco GaidoMattia Antonino Di GangiMatteo NegriMauro CettoloMarco TurchiPublished in: INTERSPEECH (2020)
Keyphrases
- automatically segmented
- speech recognition
- machine translation
- recognition engine
- spoken language
- query translation
- information retrieval
- probabilistic model
- audio visual
- speech synthesis
- speaker recognition
- hearing impaired
- neural network
- endpoint detection
- text to speech
- spoken dialogue systems
- speaker identification
- statistical machine translation
- noisy environments
- speech signal
- digital image processing
- language model