Eigenvoice Synthesis based on Model Editing for Speaker Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918083249045504 |
|---|---|
| author | Murata, Masato Miyazaki, Koichi Koriyama, Tomoki Toda, Tomoki |
| author_facet | Murata, Masato Miyazaki, Koichi Koriyama, Tomoki Toda, Tomoki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03377 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Eigenvoice Synthesis based on Model Editing for Speaker Generation Murata, Masato Miyazaki, Koichi Koriyama, Tomoki Toda, Tomoki Sound Audio and Speech Processing 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. |
| title | Eigenvoice Synthesis based on Model Editing for Speaker Generation |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.03377 |