Hear Your Face: Face-based voice conversion with F0 estimation

Autor:	Lee, Jaejun, Oh, Yoori, Hwang, Injune, Lee, Kyogu
Rok vydání:	2024
Předmět:	Computer Science - Sound Computer Science - Computer Vision and Pattern Recognition Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	This paper delves into the emerging field of face-based voice conversion, leveraging the unique relationship between an individual's facial features and their vocal characteristics. We present a novel face-based voice conversion framework that particularly utilizes the average fundamental frequency of the target speaker, derived solely from their facial images. Through extensive analysis, our framework demonstrates superior speech generation quality and the ability to align facial features with voice characteristics, including tracking of the target speaker's fundamental frequency. Comment: Interspeech 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.09802 Zobrazit plný text záznamu View this record from Arxiv