Related papers: Echoes: A semantically-aligned music deepfake dete…
Representation learning focused on disentangling the underlying factors of variation in given data has become an important area of research in machine learning. However, most of the studies in this area have relied on datasets from the…
We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data. The dataset covers a large range…
Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…
Many datasets have been designed to further the development of fake audio detection. However, fake utterances in previous datasets are mostly generated by altering timbre, prosody, linguistic content or channel noise of original audio.…
Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse speakers, since generation techniques evolve quickly. Despite…
Large Language Models and commercial speech synthesis systems now enable highly realistic AI-generated voice scams (vishing), raising urgent concerns about deception at scale. Yet it remains unclear whether individuals can reliably…
The rapid advancement of artificial intelligence (AI) has enabled sophisticated audio generation and voice cloning technologies, posing significant security risks for applications reliant on voice authentication. While existing datasets and…
Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical…
Advancements in artificial intelligence and machine learning have significantly improved synthetic speech generation. This paper explores diffusion models, a novel method for creating realistic synthetic speech. We create a diffusion…
Deepfake detection automatically recognizes the manipulated medias through the analysis of the difference between manipulated and non-altered videos. It is natural to ask which are the top performers among the existing deepfake detection…
This research explores the positive application of deepfake technology for upper body generation, specifically sign language for the Deaf and Hard of Hearing (DHoH) community. Given the complexity of sign language and the scarcity of…
Automatic recognition of insect sound could help us understand changing biodiversity trends around the world -- but insect sounds are challenging to recognize even for deep learning. We present a new dataset comprised of 26399 audio files,…
Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of generalization. Recent…
Obtaining large-scale human-labeled datasets to train acoustic representation models is a very challenging task. On the contrary, we can easily collect data with machine-generated labels. In this work, we propose to exploit…
Multi-channel audio alignment is a key requirement in bioacoustic monitoring, spatial audio systems, and acoustic localization. However, existing methods often struggle to address nonlinear clock drift and lack mechanisms for quantifying…
Recent advances in Text-to-Speech (TTS) and Voice-Conversion (VC) using generative Artificial Intelligence (AI) technology have made it possible to generate high-quality and realistic human-like audio. This poses growing challenges in…
Recent progress in audio generation models has made it possible to create highly realistic and immersive soundscapes, which are now widely used in film and virtual-reality-related applications. However, these audio generators also raise…
Measuring 3D geometric structures of indoor scenes requires dedicated depth sensors, which are not always available. Echo-based depth estimation has recently been studied as a promising alternative solution. All previous studies have…
In this paper, we introduce the concept of forensic similarity in the speech deepfake detection domain, which aims to determine whether two audio segments share the same underlying forensic traces. Our approach is inspired by prior work in…
With the continuous development of deep learning-based speech conversion and speech synthesis technologies, the cybersecurity problem posed by fake audio has become increasingly serious. Previously proposed models for defending against fake…