Voice Aging with Audio-Visual Style Transfer
This work addresses voice aging for applications in entertainment or accessibility, but it is incremental as it adapts existing face aging techniques to the audio domain.
The paper tackles the problem of voice aging by applying style transfer to transform a speaker's voice to sound younger or older, using a CNN trained on voice and face data from Common Voice and VoxCeleb datasets, and demonstrates the method on a mobile app.
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.