ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909593131548672 |
|---|---|
| author | Wang, Xin Delgado, Héctor Tak, Hemlata Jung, Jee-weon Shim, Hye-jin Todisco, Massimiliano Kukanov, Ivan Liu, Xuechen Sahidullah, Md Kinnunen, Tomi Evans, Nicholas Lee, Kong Aik Yamagishi, Junichi Jeong, Myeonghun Zhu, Ge Zang, Yongyi Zhang, You Maiti, Soumi Lux, Florian Müller, Nicolas Zhang, Wangyou Sun, Chengzhe Hou, Shuwei Lyu, Siwei Maguer, Sébastien Le Gong, Cheng Guo, Hanjie Chen, Liping Singh, Vishwanath |
| author_facet | Wang, Xin Delgado, Héctor Tak, Hemlata Jung, Jee-weon Shim, Hye-jin Todisco, Massimiliano Kukanov, Ivan Liu, Xuechen Sahidullah, Md Kinnunen, Tomi Evans, Nicholas Lee, Kong Aik Yamagishi, Junichi Jeong, Myeonghun Zhu, Ge Zang, Yongyi Zhang, You Maiti, Soumi Lux, Florian Müller, Nicolas Zhang, Wangyou Sun, Chengzhe Hou, Shuwei Lyu, Siwei Maguer, Sébastien Le Gong, Cheng Guo, Hanjie Chen, Liping Singh, Vishwanath |
| contents | ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake attacks as well as the design of detection solutions. We introduce the ASVspoof 5 database which is generated in a crowdsourced fashion from data collected in diverse acoustic conditions (cf. studio-quality data for earlier ASVspoof databases) and from ~2,000 speakers (cf. ~100 earlier). The database contains attacks generated with 32 different algorithms, also crowdsourced, and optimised to varying degrees using new surrogate detection models. Among them are attacks generated with a mix of legacy and contemporary text-to-speech synthesis and voice conversion models, in addition to adversarial attacks which are incorporated for the first time. ASVspoof 5 protocols comprise seven speaker-disjoint partitions. They include two distinct partitions for the training of different sets of attack models, two more for the development and evaluation of surrogate detection models, and then three additional partitions which comprise the ASVspoof 5 training, development and evaluation sets. An auxiliary set of data collected from an additional 30k speakers can also be used to train speaker encoders for the implementation of attack algorithms. Also described herein is an experimental validation of the new ASVspoof 5 database using a set of automatic speaker verification and spoof/deepfake baseline detectors. With the exception of protocols and tools for the generation of spoofed/deepfake speech, the resources described in this paper, already used by participants of the ASVspoof 5 challenge in 2024, are now all freely available to the community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08857 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech Wang, Xin Delgado, Héctor Tak, Hemlata Jung, Jee-weon Shim, Hye-jin Todisco, Massimiliano Kukanov, Ivan Liu, Xuechen Sahidullah, Md Kinnunen, Tomi Evans, Nicholas Lee, Kong Aik Yamagishi, Junichi Jeong, Myeonghun Zhu, Ge Zang, Yongyi Zhang, You Maiti, Soumi Lux, Florian Müller, Nicolas Zhang, Wangyou Sun, Chengzhe Hou, Shuwei Lyu, Siwei Maguer, Sébastien Le Gong, Cheng Guo, Hanjie Chen, Liping Singh, Vishwanath Audio and Speech Processing ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake attacks as well as the design of detection solutions. We introduce the ASVspoof 5 database which is generated in a crowdsourced fashion from data collected in diverse acoustic conditions (cf. studio-quality data for earlier ASVspoof databases) and from ~2,000 speakers (cf. ~100 earlier). The database contains attacks generated with 32 different algorithms, also crowdsourced, and optimised to varying degrees using new surrogate detection models. Among them are attacks generated with a mix of legacy and contemporary text-to-speech synthesis and voice conversion models, in addition to adversarial attacks which are incorporated for the first time. ASVspoof 5 protocols comprise seven speaker-disjoint partitions. They include two distinct partitions for the training of different sets of attack models, two more for the development and evaluation of surrogate detection models, and then three additional partitions which comprise the ASVspoof 5 training, development and evaluation sets. An auxiliary set of data collected from an additional 30k speakers can also be used to train speaker encoders for the implementation of attack algorithms. Also described herein is an experimental validation of the new ASVspoof 5 database using a set of automatic speaker verification and spoof/deepfake baseline detectors. With the exception of protocols and tools for the generation of spoofed/deepfake speech, the resources described in this paper, already used by participants of the ASVspoof 5 challenge in 2024, are now all freely available to the community. |
| title | ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2502.08857 |