Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement.
Rui-Chen ZhengYang AiZhen-Hua LingPublished in: CoRR (2023)
Keyphrases
- audio visual
- visual data
- image data
- image database
- input image
- multi modal
- image classification
- ultrasound images
- object recognition
- image features
- noisy environments
- image retrieval
- image collections
- speech enhancement
- background noise
- feature points
- edge detection
- information retrieval
- visual information
- image content
- multimedia
- vocal tract