1 code implementation • 3 Apr 2024 • Natalia Tomashenko, Xiaoxiao Miao, Pierre Champion, Sarina Meyer, Xin Wang, Emmanuel Vincent, Michele Panariello, Nicholas Evans, Junichi Yamagishi, Massimiliano Todisco
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.
2 code implementations • 25 Sep 2023 • Michele Panariello, Francesco Nespoli, Massimiliano Todisco, Nicholas Evans
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 is resynthesized using a vocoder.
no code implementations • 27 Aug 2023 • Oubaida Chouchane, Michele Panariello, Chiara Galdi, Massimiliano Todisco, Nicholas Evans
This study investigates the impact of gender information on utility, privacy, and fairness in voice biometric systems, guided by the General Data Protection Regulation (GDPR) mandates, which underscore the need for minimizing the processing and storage of private and sensitive data, and ensuring fairness in automated decision-making systems.
no code implementations • 17 Jul 2023 • Michele Panariello, Massimiliano Todisco, Nicholas Evans
For the most popular x-vector-based approaches to speaker anonymisation, the bulk of the anonymisation can stem from vocoding rather than from the core anonymisation function which is used to substitute an original speaker x-vector with that of a fictitious pseudo-speaker.
no code implementations • 5 Jul 2023 • Oubaïda Chouchane, Michele Panariello, Oualid Zari, Ismet Kerenciler, Imen Chihaoui, Massimiliano Todisco, Melek Önen
In this paper, we present an adversarial Auto-Encoder--based approach to hide gender-related information in speaker embeddings, while preserving their effectiveness for speaker verification.
1 code implementation • 13 Jun 2023 • Michele Panariello, Wanying Ge, Hemlata Tak, Massimiliano Todisco, Nicholas Evans
We present Malafide, a universal adversarial attack against automatic speaker verification (ASV) spoofing countermeasures (CMs).
1 code implementation • 5 Jun 2023 • Michele Panariello, Massimiliano Todisco, Nicholas Evans
State-of-the-art approaches to speaker anonymization typically employ some form of perturbation function to conceal speaker information contained within an x-vector embedding, then resynthesize utterances in the voice of a new pseudo-speaker using a vocoder.
1 code implementation • 7 Apr 2021 • Wanying Ge, Michele Panariello, Jose Patino, Massimiliano Todisco, Nicholas Evans
This paper reports the first successful application of a differentiable architecture search (DARTS) approach to the deepfake and spoofing detection problems.