Zobrazeno 1 - 10
of 22 997
pro vyhledávání: '"Kinnunen A"'
Autor:
Navistki Pavel, Lucy Garrison, Craig Tanner, Kinnunen Anna, Youmans Nate, Marie Lucy Hannah, Budavich Rachel, Ranahan William, Resor Stuart
Publikováno v:
E3S Web of Conferences, Vol 497, p 02017 (2024)
In the current dynamic educational landscape, the challenge of imparting engineering education is increasingly felt by both educators and students worldwide. Universities are striving to furnish students with the essential skills and knowledge that w
Externí odkaz:
https://doaj.org/article/beb65a506f184c23b0747563f625e77b
Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge. The proliferation of speech deepfakes on social media underscores the need for systems
Externí odkaz:
http://arxiv.org/abs/2410.20578
We propose a novel approach for spoofed speech characterization through explainable probabilistic attribute embeddings. In contrast to high-dimensional raw embeddings extracted from a spoofing countermeasure (CM) whose dimensions are not easy to inte
Externí odkaz:
http://arxiv.org/abs/2409.11027
Autor:
Kinnunen, Jami J.
The Poisson spot is a fascinating lecture demonstration. Its simple explanation can lead to further questions, not only the one posed in the title, but also questions such as why the simple model that considers only light passing just outside the sph
Externí odkaz:
http://arxiv.org/abs/2408.13894
Computing education widely applies general learning theories and pedagogical practices. However, computing also includes specific disciplinary knowledge and skills, e.g., programming and software development methods, for which there has been a long h
Externí odkaz:
http://arxiv.org/abs/2409.12245
Autor:
Wang, Xin, Delgado, Hector, 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
ASVspoof 5 is the fifth edition in a series of challenges that promote the study of speech spoofing and deepfake attacks, and the design of detection solutions. Compared to previous challenges, the ASVspoof 5 database is built from crowdsourced data
Externí odkaz:
http://arxiv.org/abs/2408.08739
Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. We propose a spoofing-robust ASV system optimized directly for the recently introduced architecture-agnostic detection cost function (a-DCF), which allows targeting a de
Externí odkaz:
http://arxiv.org/abs/2407.04034
Current trends in audio anti-spoofing detection research strive to improve models' ability to generalize across unseen attacks by learning to identify a variety of spoofing artifacts. This emphasis has primarily focused on the spoof class. Recently,
Externí odkaz:
http://arxiv.org/abs/2406.17246
Fusing outputs from automatic speaker verification (ASV) and spoofing countermeasure (CM) is expected to make an integrated system robust to zero-effort imposters and synthesized spoofing attacks. Many score-level fusion methods have been proposed, b
Externí odkaz:
http://arxiv.org/abs/2406.10836
Autor:
Singh, Vishwanath Pratap, Malato, Federico, Hautamaki, Ville, Sahidullah, Md., Kinnunen, Tomi
Publikováno v:
Interspeech 2024
While automatic speech recognition (ASR) greatly benefits from data augmentation, the augmentation recipes themselves tend to be heuristic. In this paper, we address one of the heuristic approach associated with balancing the right amount of augmente
Externí odkaz:
http://arxiv.org/abs/2406.09999