Giters

mpc001 / Lipreading_using_Temporal_Convolutional_Networks

ICASSP'22 Training Strategies for Improved Lip-Reading; ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why does training data need babble noise?

zhangyikaii opened this issue · comments

commented

Hi,

I'm a beginner in this field. Why do you need babble noise during training? That's what's happening here.

Thank you very much.

commented

Hello, noise injection is a data augmentation for audio-only and audio-visual models, which helps stabilise the model in a noisy environment.