Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement through Knowledge Distillation.

Rui-Chen Zheng Yang Ai Zhen-Hua Ling

Published in: CoRR (2023)

Keyphrases

audio visual
visual data
image data
image database
multi modal
input image
visual information
image collections
three dimensional
ultrasound images
image retrieval
image classification
image features
speech enhancement
vocal tract
feature points
noise reduction
information retrieval