SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917779702022144 |
|---|---|
| author | Xue, Liumeng Wang, Chaoren Wang, Mingxuan Zhang, Xueyao Han, Jun Wu, Zhizheng |
| author_facet | Xue, Liumeng Wang, Chaoren Wang, Mingxuan Zhang, Xueyao Han, Jun Wu, Zhizheng |
| contents | In this study, we present SingVisio, an interactive visual analysis system that aims to explain the diffusion model used in singing voice conversion. SingVisio provides a visual display of the generation process in diffusion models, showcasing the step-by-step denoising of the noisy spectrum and its transformation into a clean spectrum that captures the desired singer's timbre. The system also facilitates side-by-side comparisons of different conditions, such as source content, melody, and target timbre, highlighting the impact of these conditions on the diffusion generation process and resulting conversions. Through comparative and comprehensive evaluations, SingVisio demonstrates its effectiveness in terms of system design, functionality, explainability, and user-friendliness. It offers users of various backgrounds valuable learning experiences and insights into the diffusion model for singing voice conversion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12660 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion Xue, Liumeng Wang, Chaoren Wang, Mingxuan Zhang, Xueyao Han, Jun Wu, Zhizheng Sound Human-Computer Interaction Audio and Speech Processing In this study, we present SingVisio, an interactive visual analysis system that aims to explain the diffusion model used in singing voice conversion. SingVisio provides a visual display of the generation process in diffusion models, showcasing the step-by-step denoising of the noisy spectrum and its transformation into a clean spectrum that captures the desired singer's timbre. The system also facilitates side-by-side comparisons of different conditions, such as source content, melody, and target timbre, highlighting the impact of these conditions on the diffusion generation process and resulting conversions. Through comparative and comprehensive evaluations, SingVisio demonstrates its effectiveness in terms of system design, functionality, explainability, and user-friendliness. It offers users of various backgrounds valuable learning experiences and insights into the diffusion model for singing voice conversion. |
| title | SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion |
| topic | Sound Human-Computer Interaction Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.12660 |