WavPrompt: Towards Few-Shot Spoken Language Understanding with Frozen Language Models.
Heting GaoJunrui NiKaizhi QianYang ZhangShiyu ChangMark Hasegawa-JohnsonPublished in: INTERSPEECH (2022)
Keyphrases
- language understanding
- language model
- natural language understanding
- language modeling
- n gram
- dialogue management
- probabilistic model
- language processing
- speech recognition
- information retrieval
- document retrieval
- query expansion
- dialogue system
- video shots
- video data
- retrieval model
- semantic interpretation
- natural language
- spoken dialogue systems
- test collection
- video content
- vector space model
- key frames
- language modelling
- visual features
- cognitive psychology
- general knowledge
- smoothing methods
- statistical language models
- news video
- machine learning
- language models for information retrieval
- natural language processing
- semantic analysis
- text categorization