SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion
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...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Xue, Liumeng Wang, Chaoren Wang, Mingxuan Zhang, Xueyao Han, Jun Wu, Zhizheng |
| description | 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. |
| doi_str_mv | 10.48550/arxiv.2402.12660 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2402_12660</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2402_12660</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-7db383ceed2ae1b3f1b0fa15b07f0d7a98832cf87b518ff85abbd3a03b9e96df3</originalsourceid><addsrcrecordid>eNotj8lOwzAURb1hgQofwKrvBxI81LHDrgqjKGLRqtvoOfZDlkKMHFrRvycpSFe6iztIh7EbwcuV1ZrfYv6Jx1KuuCyFrCp-yV63cfjYxzGmO5jsgD2sB-xP37EbIRHcR6LDlA7wlnzogVKGeTIJ9il2AZo0HEOeK1fsgrAfw_W_L9ju8WHXPBeb96eXZr0psDK8MN4pq7oQvMQgnCLhOKHQjhvi3mBtrZIdWeO0sERWo3NeIVeuDnXlSS3Y8u_2TNN-5fiJ-dTOVO2ZSv0CvvhIvQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion</title><source>arXiv.org</source><creator>Xue, Liumeng ; Wang, Chaoren ; Wang, Mingxuan ; Zhang, Xueyao ; Han, Jun ; Wu, Zhizheng</creator><creatorcontrib>Xue, Liumeng ; Wang, Chaoren ; Wang, Mingxuan ; Zhang, Xueyao ; Han, Jun ; Wu, Zhizheng</creatorcontrib><description>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.</description><identifier>DOI: 10.48550/arxiv.2402.12660</identifier><language>eng</language><subject>Computer Science - Human-Computer Interaction ; Computer Science - Sound</subject><creationdate>2024-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2402.12660$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2402.12660$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Xue, Liumeng</creatorcontrib><creatorcontrib>Wang, Chaoren</creatorcontrib><creatorcontrib>Wang, Mingxuan</creatorcontrib><creatorcontrib>Zhang, Xueyao</creatorcontrib><creatorcontrib>Han, Jun</creatorcontrib><creatorcontrib>Wu, Zhizheng</creatorcontrib><title>SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion</title><description>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.</description><subject>Computer Science - Human-Computer Interaction</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8lOwzAURb1hgQofwKrvBxI81LHDrgqjKGLRqtvoOfZDlkKMHFrRvycpSFe6iztIh7EbwcuV1ZrfYv6Jx1KuuCyFrCp-yV63cfjYxzGmO5jsgD2sB-xP37EbIRHcR6LDlA7wlnzogVKGeTIJ9il2AZo0HEOeK1fsgrAfw_W_L9ju8WHXPBeb96eXZr0psDK8MN4pq7oQvMQgnCLhOKHQjhvi3mBtrZIdWeO0sERWo3NeIVeuDnXlSS3Y8u_2TNN-5fiJ-dTOVO2ZSv0CvvhIvQ</recordid><startdate>20240219</startdate><enddate>20240219</enddate><creator>Xue, Liumeng</creator><creator>Wang, Chaoren</creator><creator>Wang, Mingxuan</creator><creator>Zhang, Xueyao</creator><creator>Han, Jun</creator><creator>Wu, Zhizheng</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240219</creationdate><title>SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion</title><author>Xue, Liumeng ; Wang, Chaoren ; Wang, Mingxuan ; Zhang, Xueyao ; Han, Jun ; Wu, Zhizheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-7db383ceed2ae1b3f1b0fa15b07f0d7a98832cf87b518ff85abbd3a03b9e96df3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Human-Computer Interaction</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Xue, Liumeng</creatorcontrib><creatorcontrib>Wang, Chaoren</creatorcontrib><creatorcontrib>Wang, Mingxuan</creatorcontrib><creatorcontrib>Zhang, Xueyao</creatorcontrib><creatorcontrib>Han, Jun</creatorcontrib><creatorcontrib>Wu, Zhizheng</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Xue, Liumeng</au><au>Wang, Chaoren</au><au>Wang, Mingxuan</au><au>Zhang, Xueyao</au><au>Han, Jun</au><au>Wu, Zhizheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion</atitle><date>2024-02-19</date><risdate>2024</risdate><abstract>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.</abstract><doi>10.48550/arxiv.2402.12660</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2402.12660 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2402_12660 |
| source | arXiv.org |
| subjects | Computer Science - Human-Computer Interaction Computer Science - Sound |
| title | SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T02%3A41%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SingVisio:%20Visual%20Analytics%20of%20Diffusion%20Model%20for%20Singing%20Voice%20Conversion&rft.au=Xue,%20Liumeng&rft.date=2024-02-19&rft_id=info:doi/10.48550/arxiv.2402.12660&rft_dat=%3Carxiv_GOX%3E2402_12660%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |