An Empirical Study of Visual Features for DNN based Audio-Visual Speech Enhancement in Multi-talker Environments.
Shrishti Saha ShetuSoumitro ChakrabartyEmanuël Anco Peter HabetsPublished in: CoRR (2020)
Keyphrases
- audio visual
- visual features
- visual information
- visual data
- speech enhancement
- visual content
- noisy environments
- image classification
- multi modal
- image retrieval
- audio features
- sound source
- image collections
- low level
- noise reduction
- keywords
- image annotation
- low level features
- signal to noise ratio
- key frames
- multimedia
- speech signal
- video data
- speaker verification
- high level