Related papers: DAST: A Dual-Stream Voice Anonymization Attacker w…

Although the bulk of the research in privacy and statistical disclosure control is designed for static data, more and more data are often collected as continuous streams, and extensions of popular privacy tools and models have been proposed…

Recent progress in generative AI technology has made audio deepfakes remarkably more realistic. While current research on anti-spoofing systems primarily focuses on assessing whether a given audio sample is fake or genuine, there has been…

As face recognition is widely used in diverse security-critical applications, the study of face anti-spoofing (FAS) has attracted more and more attention. Several FAS methods have achieved promising performances if the attack types in the…

Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence. Prevalent methods tackling this problem use differential privacy (DP) or obfuscation techniques to protect the privacy of…

The proliferation of highly realistic singing voice deepfakes presents a significant challenge to protecting artist likeness and content authenticity. Automatic singer identification in vocal deepfakes is a promising avenue for artists and…

We present Multiscale Audio Spectrogram Transformer (MAST) for audio classification, which brings the concept of multiscale feature hierarchies to the Audio Spectrogram Transformer (AST). Given an input audio spectrogram, we first patchify…

Modern Voice Control Systems (VCS) rely on the collaboration of Automatic Speech Recognition (ASR) and Speaker Recognition (SR) for secure interaction. However, prior adversarial attacks typically target these tasks in isolation,…

Voice activity detection is the task of detecting speech regions in a given audio stream or recording. First, we design a neural network combining trainable filters and recurrent layers to tackle voice activity detection directly from the…

Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diarisation and speech recognition using a single model, a…

Automatic speech recognition (ASR) is a key technology in many services and applications. This typically requires user devices to send their speech data to the cloud for ASR decoding. As the speech signal carries a lot of information about…

End-to-end full-duplex speech models feed user audio through an always-on LLM backbone, yet the speaker privacy implications of their hidden representations remain unexamined. Following the VoicePrivacy 2024 protocol with a lazy-informed…

We address speaker-aware anti-spoofing, where prior knowledge of the target speaker is incorporated into a voice spoofing countermeasure (CM). In contrast to the frequently used speaker-independent solutions, we train the CM in a…

Air traffic control (ATC) demands multi-tasking under time pressure with high consequences of an error. This can induce stress. Detecting stress is a key point in maintaining the high safety standards of ATC. However, processing ATC voice…

Voice assistive technologies have given rise to far-reaching privacy and security concerns. In this paper we investigate whether modular automatic speech recognition (ASR) can improve privacy in voice assistive systems by combining…

Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…

Speaker adaptation systems face privacy concerns, for such systems are trained on private datasets and often overfitting. This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech…

Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant…

Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied…

Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modalities of auxiliary information such as prompts and emotion…

Deepfakes are synthetically generated media often devised with malicious intent. They have become increasingly more convincing with large training datasets advanced neural networks. These fakes are readily being misused for slander,…