SECap: Speech Emotion Captioning with Large Language Model.
Yaoxun XuHangting ChenJianwei YuQiaochu HuangZhiyong WuShi-Xiong ZhangGuangzhi LiYi LuoRongzhi GuPublished in: AAAI (2024)
Keyphrases
- language model
- speech recognition
- word error rate
- emotion recognition
- language modeling
- emotional state
- speech signal
- information retrieval
- document retrieval
- retrieval model
- n gram
- automatic speech recognition
- language modelling
- query expansion
- probabilistic model
- test collection
- ad hoc information retrieval
- out of vocabulary
- audio visual
- context sensitive
- translation model
- statistical language models
- pseudo relevance feedback
- mixture model
- language models for information retrieval
- vector space model
- smoothing methods
- error rate
- machine learning
- document ranking
- broadcast news
- web search