SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models.
Xin ZhangDong ZhangShimin LiYaqian ZhouXipeng QiuPublished in: CoRR (2023)
Keyphrases
- language model
- speech recognition
- word error rate
- language modeling
- spoken term detection
- automatic speech recognition
- speech signal
- n gram
- document retrieval
- probabilistic model
- statistical language models
- information retrieval
- retrieval model
- vector space model
- query expansion
- test collection
- broadcast news
- audio visual
- error rate
- mixture model
- ad hoc information retrieval
- smoothing methods
- retrieval systems
- pseudo relevance feedback
- handwriting recognition
- language modelling