Saved in:
Bibliographic Details
Main Authors: Zhang, Tian-Hao, Zhang, Jiawei, Wang, Jun, Qian, Xinyuan, Yin, Xu-Cheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.03181
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909580365135872
author Zhang, Tian-Hao
Zhang, Jiawei
Wang, Jun
Qian, Xinyuan
Yin, Xu-Cheng
author_facet Zhang, Tian-Hao
Zhang, Jiawei
Wang, Jun
Qian, Xinyuan
Yin, Xu-Cheng
contents Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces, thereby restricting effective speech synthesis from applying to vast potential usage scenarios with diverse characters and image styles. To solve this issue, we introduce a novel FaceSpeak approach. It extracts salient identity characteristics and emotional representations from a wide variety of image styles. Meanwhile, it mitigates the extraneous information (e.g., background, clothing, and hair color, etc.), resulting in synthesized speech closely aligned with a character's persona. Furthermore, to overcome the scarcity of multi-modal TTS data, we have devised an innovative dataset, namely Expressive Multi-Modal TTS, which is diligently curated and annotated to facilitate research in this domain. The experimental results demonstrate our proposed FaceSpeak can generate portrait-aligned voice with satisfactory naturalness and quality.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03181
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles
Zhang, Tian-Hao
Zhang, Jiawei
Wang, Jun
Qian, Xinyuan
Yin, Xu-Cheng
Sound
Artificial Intelligence
Audio and Speech Processing
Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces, thereby restricting effective speech synthesis from applying to vast potential usage scenarios with diverse characters and image styles. To solve this issue, we introduce a novel FaceSpeak approach. It extracts salient identity characteristics and emotional representations from a wide variety of image styles. Meanwhile, it mitigates the extraneous information (e.g., background, clothing, and hair color, etc.), resulting in synthesized speech closely aligned with a character's persona. Furthermore, to overcome the scarcity of multi-modal TTS data, we have devised an innovative dataset, namely Expressive Multi-Modal TTS, which is diligently curated and annotated to facilitate research in this domain. The experimental results demonstrate our proposed FaceSpeak can generate portrait-aligned voice with satisfactory naturalness and quality.
title FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2501.03181