Related papers: Jigsaw Cryptanalysis of Audio Scrambling Systems
Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…
Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning…
Reconstructing continuous signals from a small number of discrete samples is a fundamental problem across science and engineering. In practice, we are often interested in signals with 'simple' Fourier structure, such as bandlimited,…
Security of multimedia data is a major concern due to its widespread transmission over various communication channels. Hence design and study of good image encryption schemes has become a major research topic. During the last few decades,…
Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…
The increasing realism of synthetic speech generated by advanced text-to-speech (TTS) models, coupled with post-processing and laundering techniques, presents a significant challenge for audio forensic detection. In this paper, we introduce…
Recent advances in AudioLLMs have enabled spoken dialogue systems to move beyond turn-based interaction toward real-time full-duplex communication, where the agent must decide when to speak, yield, or interrupt while the user is still…
Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, direct merging is challenging when the models are not aligned in…
This paper focuses on audio deepfake detection under real-world communication degradations, with an emphasis on ultra-short inputs (0.5-2.0s), targeting the capability to detect synthetic speech at a conversation opening, e.g., when a…
As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where…
The Euclidean distance between wavelet scattering transform coefficients (known as paths) provides informative gradients for perceptual quality assessment of deep inverse problems in computer vision, speech, and audio processing. However,…
It is well-known that speakers who entrain to one another have more successful conversations than those who do not. Previous research has shown that interlocutors entrain on linguistic features in both written and spoken monolingual…
In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies…
The field of steganography has experienced a surge of interest due to the recent advancements in AI-powered techniques, particularly in the context of multimodal setups that enable the concealment of signals within signals of a different…
This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo. Our approach is based on developing an extension for the conventional distortion condition…
A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models' robustness against perturbations…
Linguistic steganography aims to conceal information within natural language text without being detected. An effective steganography approach should encode the secret message into a minimal number of language tokens while preserving the…
Often the question arises whether $Y$ can be predicted based on $X$ using a certain model. Especially for highly flexible models such as neural networks one may ask whether a seemingly good prediction is actually better than fitting pure…
In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion…
This work describes our group's submission to the PROCESS Challenge 2024, with the goal of assessing cognitive decline through spontaneous speech, using three guided clinical tasks. This joint effort followed a holistic approach,…