Related papers: Introducing the VoicePrivacy Initiative
Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is…
Employee voice and workplace democracy have a positive impact on employee wellbeing and the performance of organizations. In this paper, we conducted interviews with employees to identify facilitators and inhibitors for the voice within the…
In an ideal world, deployed machine learning models will enhance our society. We hope that those models will provide unbiased and ethical decisions that will benefit everyone. However, this is not always the case; issues arise during the…
The Far-Field Speaker Verification Challenge 2020 (FFSVC20) is designed to boost the speaker verification research with special focus on far-field distributed microphone arrays under noisy conditions in real scenarios. The objectives of…
Researchers often face the problem of needing to protect the privacy of subjects while also needing to integrate data that contains personal information from diverse data sources in order to conduct their research. The advent of…
Research on data confidentiality, integrity and availability is gaining momentum in the ICT community, due to the intrinsically insecure nature of the Internet. While many distributed systems and services are now based on secure…
Low-frequency audio has been proposed as a promising privacy-preserving modality to study social dynamics in real-world settings. To this end, researchers have developed wearable devices that can record audio at frequencies as low as 1250…
This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation…
To prove that a dataset is sufficiently anonymized, many privacy policies suggest that a re-identification risk assessment be performed, but do not provide a precise methodology for doing so, leaving the industry alone with the problem.…
The 2020 Personalized Voice Trigger Challenge (PVTC2020) addresses two different research problems a unified setup: joint wake-up word detection with speaker verification on close-talking single microphone data and far-field multi-channel…
Enormous amounts of data collected from social networks or other online platforms are being published for the sake of statistics, marketing, and research, among other objectives. The consequent privacy and data security concerns have…
IoT is an emerging area in which we expect to have billions of devices connected to the Internet by 2020. IoT applications can offer many benefits to environments, society and the economy through the interconnection and cooperation of smart…
LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only suppression (omitting sensitive information) and…
This paper explores various attack scenarios on a voice anonymization system using embeddings alignment techniques. We use Wasserstein-Procrustes (an algorithm initially designed for unsupervised translation) or Procrustes analysis to match…
Voice Service Providers (VSPs) participating in VoIP peering frequently want to withhold their identity and related privacy-sensitive information from other parties during the VoIP communication. A number of existing documents on VoIP…
For sensitive text data to be shared among NLP researchers and practitioners, shared documents need to comply with data protection and privacy laws. There is hence a growing interest in automated approaches for text anonymization. However,…
The external evaluation of AI systems is increasingly recognised as a crucial approach for understanding their potential risks. However, facilitating external evaluation in practice faces significant challenges in balancing evaluators' need…
Many anonymous communication networks (ACNs) with different privacy goals have been developed. However, there are no accepted formal definitions of privacy and ACNs often define their goals and adversary models ad hoc. However, for the…
The "VOiCES from a Distance Challenge 2019" is designed to foster research in the area of speaker recognition and automatic speech recognition (ASR) with the special focus on single channel distant/far-field audio, under noisy conditions.…
We present a number of systems for the Voice Privacy Challenge, including voice conversion based systems such as the kNN-VC method and the WavLM voice Conversion method, and text-to-speech (TTS) based systems including Whisper-VITS. We…