Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks.
Jen-Cheng HouSyu-Siang WangYing-Hui LaiYu TsaoHsiu-Wen ChangHsin-Min WangPublished in: IEEE Trans. Emerg. Top. Comput. Intell. (2018)
Keyphrases
- audio visual
- convolutional neural networks
- speech enhancement
- multi modal
- noise reduction
- noisy environments
- signal to noise ratio
- single channel
- speech signal
- visual information
- linear prediction
- multi stream
- visual data
- vocal tract
- multimodal fusion
- smoothing algorithm
- multimedia
- background noise
- audio features
- wiener filter
- sound source
- e learning
- speaker identification
- edge detection
- high dimensional
- multiscale
- information retrieval