SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities.
Dong ZhangShimin LiXin ZhangJun ZhanPengyu WangYaqian ZhouXipeng QiuPublished in: EMNLP (Findings) (2023)
Keyphrases
- language model
- cross modal
- multi modal
- language modeling
- probabilistic model
- document retrieval
- n gram
- test collection
- information retrieval
- retrieval model
- query expansion
- multimedia retrieval
- multimedia databases
- smoothing methods
- visual recognition
- image retrieval
- vector space model
- pseudo relevance feedback
- visual similarity
- search engine
- image understanding
- information retrieval systems
- image database
- visual data
- relevance model
- multimedia
- metadata