Generative Spoken Language Model based on continuous word-sized audio tokens.
Robin AlgayresYossi AdiTu Anh NguyenJade CopetGabriel SynnaeveBenoît SagotEmmanuel DupouxPublished in: CoRR (2023)
Keyphrases
- spoken language
- speech recognizer
- spontaneous speech
- automatic transcription
- recognition errors
- linguistic knowledge
- dialogue system
- semantic analysis
- language processing
- broadcast news
- co occurrence
- generative model
- n gram
- natural language
- word sense disambiguation
- automatic speech recognition
- data mining
- context aware
- keywords
- machine learning