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

被引：0

作者：

Lee, Jaejun ^{[1
]}

Oh, Yoori ^{[1
]}

Hwang, Injune ^{[1
]}

Lee, Kyogu ^{[1
,2
,3
]}

机构：

[1] Seoul Natl Univ, Dept Intelligence & Informat, Seoul, South Korea

[2] Seoul Natl Univ, Interdisciplinary Program Artificial Intelligence, Seoul, South Korea

[3] Seoul Natl Univ, Artificial Intelligence Inst, Seoul, South Korea

来源：

INTERSPEECH 2024 | 2024年

关键词：

voice conversion; face/voice association; cross modal generation; speaker embedding; IDENTITY;

D O I：

10.21437/Interspeech.2024-232

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：4378 / 4382

页数：5

共 31 条

[1]

Afouras T, 2018, Arxiv, DOI arXiv:1809.00496

[2] Integrating face and voice in person perception [J].

Campanella, Salvatore ;

Belin, Pascal .

TRENDS IN COGNITIVE SCIENCES, 2007, 11 (12) :535-543

[3]

Choi H. -S., 2022, 11 INT C LEARNING

[4]

Choi H.-S., 2019, INT C LEARNING REPR

[5]

Choi HS, 2021, ADV NEUR IN, V34

[6]

Dinh L, 2017, Arxiv, DOI [arXiv:1605.08803, 10.48550/arXiv.1605.08803 1605.08803]

[7]

Dosovitskiy A, 2021, Arxiv, DOI arXiv:2010.11929

[8] Face2Speech: Towards Multi-Speaker Text-to-Speech Synthesis Using an Embedding Vector Predicted from a Face Image [J].

Goto, Shunsuke ;

Onishi, Kotaro ;

Saito, Yuki ;

Tachibana, Kentaro ;

Mori, Koichiro .

INTERSPEECH 2020, 2020, :1321-1325

[9] Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder [J].

Hsu, Chin-Cheng ;

Hwang, Hsin-Te ;

Wu, Yi-Chiao ;

Tsao, Yu ;

Wang, Hsin-Min .

2016 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2016,

[10] HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units [J].

Hsu, Wei-Ning ;

Bolte, Benjamin ;

Tsai, Yao-Hung Hubert ;

Lakhotia, Kushal ;

Salakhutdinov, Ruslan ;

Mohamed, Abdelrahman .

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 :3451-3460

← 1 2 3 4 →