BUT Systems and Analyses for the ASVspoof 5 Challenge
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910571392139264 |
|---|---|
| author | Rohdin, Johan Zhang, Lin Plchot, Oldřich Staněk, Vojtěch Mihola, David Peng, Junyi Stafylakis, Themos Beveraki, Dmitriy Silnova, Anna Brukner, Jan Burget, Lukáš |
| author_facet | Rohdin, Johan Zhang, Lin Plchot, Oldřich Staněk, Vojtěch Mihola, David Peng, Junyi Stafylakis, Themos Beveraki, Dmitriy Silnova, Anna Brukner, Jan Burget, Lukáš |
| contents | This paper describes the BUT submitted systems for the ASVspoof 5 challenge, along with analyses. For the conventional deepfake detection task, we use ResNet18 and self-supervised models for the closed and open conditions, respectively. In addition, we analyze and visualize different combinations of speaker information and spoofing information as label schemes for training. For spoofing-robust automatic speaker verification (SASV), we introduce effective priors and propose using logistic regression to jointly train affine transformations of the countermeasure scores and the automatic speaker verification scores in such a way that the SASV LLR is optimized. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11152 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BUT Systems and Analyses for the ASVspoof 5 Challenge Rohdin, Johan Zhang, Lin Plchot, Oldřich Staněk, Vojtěch Mihola, David Peng, Junyi Stafylakis, Themos Beveraki, Dmitriy Silnova, Anna Brukner, Jan Burget, Lukáš Sound Audio and Speech Processing This paper describes the BUT submitted systems for the ASVspoof 5 challenge, along with analyses. For the conventional deepfake detection task, we use ResNet18 and self-supervised models for the closed and open conditions, respectively. In addition, we analyze and visualize different combinations of speaker information and spoofing information as label schemes for training. For spoofing-robust automatic speaker verification (SASV), we introduce effective priors and propose using logistic regression to jointly train affine transformations of the countermeasure scores and the automatic speaker verification scores in such a way that the SASV LLR is optimized. |
| title | BUT Systems and Analyses for the ASVspoof 5 Challenge |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.11152 |