Extending Large Language Models for Speech and Audio Captioning.
Changli TangWenyi YuGuangzhi SunXianzhao ChenTian TanWei LiLu LuZejun MaChao ZhangPublished in: ICASSP (2024)
Keyphrases
- language model
- speech recognition
- speaker identification
- audio stream
- audio visual
- word error rate
- broadcast news
- language modeling
- document retrieval
- automatic speech recognition
- speech signal
- n gram
- probabilistic model
- retrieval model
- text to speech
- information retrieval
- spoken term detection
- audio features
- language modelling
- query expansion
- test collection
- statistical language models
- smoothing methods
- multimedia
- context sensitive
- mixture model
- multi modal
- visual information
- pseudo relevance feedback
- out of vocabulary
- query terms
- ad hoc information retrieval
- language models for information retrieval
- translation model
- visual data
- vector space model
- language model for information retrieval
- document ranking
- relevance feedback
- hidden markov models