Age-VOX-Celeb: Multi-Modal Corpus for Facial and Speech Estimation

Estimating a speaker's age from their speech is more challenging than age estimation from their face because of insufficiently available public corpora. To tackle this problem, we construct a new audio-visual age corpus named AgeVoxCeleb by annotating age labels to VoxCeleb2 videos. AgeVoxCeleb...

Full description

Saved in:
Bibliographic Details
Main Authors: Tawara, Naohiro, Ogawa, Atsunori, Kitagishi, Yuki, Kamiyama, Hosana
Format: Conference Proceeding
Language:English
Subjects:
cross-modal learning
Data models
Estimation
Robustness
Signal processing
Speech and facial age estimation
squeeze-and-excitation network
Task analysis
Training
Transfer learning
x-vector
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!