English

Eigenvoice Synthesis based on Model Editing for Speaker Generation

Sound 2025-07-08 v1 Audio and Speech Processing

Abstract

Speaker generation task aims to create unseen speaker voice without reference speech. The key to the task is defining a speaker space that represents diverse speakers to determine the generated speaker trait. However, the effective way to define this speaker space remains unclear. Eigenvoice synthesis is one of the promising approaches in the traditional parametric synthesis framework, such as HMM-based methods, which define a low-dimensional speaker space using pre-stored speaker features. This study proposes a novel DNN-based eigenvoice synthesis method via model editing. Unlike prior methods, our method defines a speaker space in the DNN model parameter space. By directly sampling new DNN model parameters in this space, we can create diverse speaker voices. Experimental results showed the capability of our method to generate diverse speakers' speech. Moreover, we discovered a gender-dominant axis in the created speaker space, indicating the potential to control speaker attributes.

Keywords

Cite

@article{arxiv.2507.03377,
  title  = {Eigenvoice Synthesis based on Model Editing for Speaker Generation},
  author = {Masato Murata and Koichi Miyazaki and Tomoki Koriyama and Tomoki Toda},
  journal= {arXiv preprint arXiv:2507.03377},
  year   = {2025}
}

Comments

Accepted by INTERSPEECH 2025

R2 v1 2026-07-01T03:46:25.226Z