Audio-Visual Multi-Channel Recognition of Overlapped Speech.
Jianwei YuBo WuRongzhi GuShi-Xiong ZhangLianwu ChenYong XuMeng YuDan SuDong YuXunying LiuHelen MengPublished in: INTERSPEECH (2020)
Keyphrases
- audio visual
- multi channel
- multi modal
- digit recognition
- visual information
- emotion recognition
- multi stream
- single channel
- visual data
- feature extraction
- audio visual speech recognition
- speaker verification
- object recognition
- multimedia
- action recognition
- image features
- search engine
- human activities
- image data
- high dimensional
- face recognition