Summary on the Multimodal Information Based Speech Processing (MISP) 2022 Challenge.
Hang ChenShilong WuYusheng DaiZhe WangJun DuChin-Hui LeeJingdong ChenShinji WatanabeSabato Marco SiniscalchiOdette ScharenborgDiyuan LiuBao-Cai YinJia PanJianqing GaoCong LiuPublished in: ICASSP (2023)
Keyphrases
- speech processing
- multimodal information
- speech recognition
- signal processing
- multimedia systems
- natural language processing
- video data
- visual data
- speaker identification
- artificial intelligence
- english text
- machine learning
- variable length
- multimedia
- database systems
- metadata
- image retrieval
- knowledge representation
- pattern recognition
- multiscale
- multimedia data
- low level features