Zobrazeno 1 - 10
of 8 455
pro vyhledávání: '"Todisco, A."'
We introduce 2D-Malafide, a novel and lightweight adversarial attack designed to deceive face deepfake detection systems. Building upon the concept of 1D convolutional perturbations explored in the speech domain, our method leverages 2D convolutional
Externí odkaz:
http://arxiv.org/abs/2408.14143
Autor:
Todisco, Massimiliano, Panariello, Michele, Wang, Xin, Delgado, Héctor, Lee, Kong Aik, Evans, Nicholas
We present Malacopula, a neural-based generalised Hammerstein model designed to introduce adversarial perturbations to spoofed speech utterances so that they better deceive automatic speaker verification (ASV) systems. Using non-linear processes to m
Externí odkaz:
http://arxiv.org/abs/2408.09300
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
Voice anonymisation can be used to help protect speaker privacy when speech data is shared with untrusted others. In most practical applications, while the voice identity should be sanitised, other attributes such as the spoken content should be pres
Externí odkaz:
http://arxiv.org/abs/2408.04306
Autor:
Panariello, Michele, Tomashenko, Natalia, Wang, Xin, Miao, Xiaoxiao, Champion, Pierre, Nourtel, Hubert, Todisco, Massimiliano, Evans, Nicholas, Vincent, Emmanuel, Yamagishi, Junichi
The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology. In this paper we present a systematic overview and analysis of the second edition held in 2022. We describe the voice anonymisation task and d
Externí odkaz:
http://arxiv.org/abs/2407.11516
When decisions are made and when personal data is treated by automated processes, there is an expectation of fairness -- that members of different demographic groups receive equitable treatment. This expectation applies to biometric systems such as a
Externí odkaz:
http://arxiv.org/abs/2404.17810
Autor:
Tomashenko, Natalia, Miao, Xiaoxiao, Champion, Pierre, Meyer, Sarina, Wang, Xin, Vincent, Emmanuel, Panariello, Michele, Evans, Nicholas, Yamagishi, Junichi, Todisco, Massimiliano
The task of the challenge is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content and emotional states. The organizers provide development and evaluation datasets and
Externí odkaz:
http://arxiv.org/abs/2404.02677
The vast majority of approaches to speaker anonymization involve the extraction of fundamental frequency estimates, linguistic features and a speaker embedding which is perturbed to obfuscate the speaker identity before an anonymized speech waveform
Externí odkaz:
http://arxiv.org/abs/2309.14129
A reliable deepfake detector or spoofing countermeasure (CM) should be robust in the face of unpredictable spoofing attacks. To encourage the learning of more generaliseable artefacts, rather than those specific only to known attacks, CMs are usually
Externí odkaz:
http://arxiv.org/abs/2309.09586
Autor:
Miao, Xiaoxiao, Wang, Xin, Cooper, Erica, Yamagishi, Junichi, Evans, Nicholas, Todisco, Massimiliano, Bonastre, Jean-François, Rouvier, Mickael
The success of deep learning in speaker recognition relies heavily on the use of large datasets. However, the data-hungry nature of deep learning methods has already being questioned on account the ethical, privacy, and legal concerns that arise when
Externí odkaz:
http://arxiv.org/abs/2309.06141