Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms

Zhang ChuYuan, Yi Jiangyan, Tao Jianhua, Wang Chenglong, Yan Xinrui


Abstract
“Recent advancements in neural speech synthesis technologies have brought aboutwidespread applications but have also raised concerns about potential misuse and abuse.Addressing these challenges is crucial, particularly in the realms of forensics and intellec-tual property protection. While previous research on source attribution of synthesizedspeech has its limitations, our study aims to fill these gaps by investigating the identifi-cation of sources in synthesized speech. We focus on analyzing speech synthesis modelfingerprints in generated speech waveforms, emphasizing the roles of the acoustic modeland vocoder. Our research, based on the multi-speaker LibriTTS dataset, reveals twokey insights: (1) both vocoders and acoustic models leave distinct, model-specific fin-gerprints on generated waveforms, and (2) vocoder fingerprints, being more dominant,may obscure those from the acoustic model. These findings underscore the presence ofmodel-specific fingerprints in both components, suggesting their potential significance insource identification applications.”
Anthology ID:
2024.ccl-1.90
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Maosong Sun, Jiye Liang, Xianpei Han, Zhiyuan Liu, Yulan He
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
1160–1171
Language:
English
URL:
https://aclanthology.org/2024.ccl-1.90/
DOI:
Bibkey:
Cite (ACL):
Zhang ChuYuan, Yi Jiangyan, Tao Jianhua, Wang Chenglong, and Yan Xinrui. 2024. Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 1160–1171, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms (ChuYuan et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-1.90.pdf