Voice Aging with Audio-Visual Style Transfer
Sound
2021-10-07 v1 Computation and Language
Machine Learning
Audio and Speech Processing
Abstract
Face aging techniques have used generative adversarial networks (GANs) and style transfer learning to transform one's appearance to look younger/older. Identity is maintained by conditioning these generative networks on a learned vector representation of the source content. In this work, we apply a similar approach to age a speaker's voice, referred to as voice aging. We first analyze the classification of a speaker's age by training a convolutional neural network (CNN) on the speaker's voice and face data from Common Voice and VoxCeleb datasets. We generate aged voices from style transfer to transform an input spectrogram to various ages and demonstrate our method on a mobile app.
Cite
@article{arxiv.2110.02411,
title = {Voice Aging with Audio-Visual Style Transfer},
author = {Justin Wilson and Sunyeong Park and Seunghye J. Wilson and Ming C. Lin},
journal= {arXiv preprint arXiv:2110.02411},
year = {2021}
}