17 citations · 50 across the 27 of their papers we have counts for
28 papers
Detecting Audio Deepfakes on the Edge:Lightweight SSL-Based Detection in a Browser Plugin
Octavian Pascu, Dan Oneata, Horia Cucu +1
Audio deepfakes are a growing challenge for the general public, as well as for journalists and fact-checkers. The latter need reliable tools to verify the authenticity of their sou…
Echoes: A semantically-aligned music deepfake detection dataset
Octavian Pascu, Dan Oneata, Horia Cucu +1
We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions. Echoes comprises 4…
Investigating self-supervised representations for audio-visual deepfake detection
Dragos-Alexandru Boldisor, Stefan Smeu, Dan Oneata +1
Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake detection remains underexplored. Unlike prior work that uses th…
Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories
Liviu Nicolae Fircă, Antonio Bărbălau, Dan Oneata +1
Can models generalize attribute knowledge across semantically and perceptually dissimilar categories? While prior work has addressed attribute prediction within narrow taxonomic or…
The mutual exclusivity bias of bilingual visually grounded speech models
Dan Oneata, Leanne Nortje, Yevgen Matusevych +1
Mutual exclusivity (ME) is a strategy where a novel word is associated with a novel object rather than a familiar one, facilitating language learning in children. Recent work has f…
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era
Dan Oneata, Desmond Elliott, Stella Frank
Human learning and conceptual representation is grounded in sensorimotor experience, in contrast to state-of-the-art foundation models. In this paper, we investigate how well such…
Unmasking real-world audio deepfakes: A data-centric approach
David Combei, Adriana Stan, Dan Oneata +2
The growing prevalence of real-world deepfakes presents a critical challenge for existing detection systems, which are often evaluated on datasets collected just for scientific pur…
TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes
Adriana Stan, David Combei, Dan Oneata +1
Deepfake detection has gained significant attention across audio, text, and image modalities, with high accuracy in distinguishing real from fake. However, identifying the exact so…
Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
Stefan Smeu, Dragos-Alexandru Boldisor, Dan Oneata +1
Good datasets are essential for developing and benchmarking any machine learning system. Their importance is even more extreme for safety critical applications such as deepfake det…
DeCLIP: Decoding CLIP representations for deepfake localization
Stefan Smeu, Elisabeta Oneata, Dan Oneata
Generative models can create entirely new images, but they can also partially modify real images in ways that are undetectable to the human eye. In this paper, we address the chall…
Improved Visually Prompted Keyword Localisation in Real Low-Resource Settings
Leanne Nortje, Dan Oneata, Gabriel Pirlogeanu +1
Given an image query, visually prompted keyword localisation (VPKL) aims to find occurrences of the depicted word in a speech collection. This can be useful when transcriptions are…
Easy, Interpretable, Effective: openSMILE for voice deepfake detection
Octavian Pascu, Dan Oneata, Horia Cucu +1
In this paper, we demonstrate that attacks in the latest ASVspoof5 dataset -- a de facto standard in the field of voice authenticity and deepfake detection -- can be identified wit…
WavLM model ensemble for audio deepfake detection
David Combei, Adriana Stan, Dan Oneata +1
Audio deepfake detection has become a pivotal task over the last couple of years, as many recent speech synthesis and voice cloning systems generate highly realistic speech samples…
Translating speech with just images
Dan Oneata, Herman Kamper
Visually grounded speech models link speech to images. We extend this connection by linking images to text via an existing image captioning system, and as a result gain the ability…
Visually Grounded Speech Models have a Mutual Exclusivity Bias
Leanne Nortje, Dan Oneaţă, Yevgen Matusevych +1
When children learn new words, they employ constraints such as the mutual exclusivity (ME) bias: a novel word is mapped to a novel object rather than a familiar one. This bias has…
Weakly-supervised deepfake localization in diffusion-generated images
Dragos Tantaru, Elisabeta Oneata, Dan Oneata
The remarkable generative capabilities of denoising diffusion models have raised new concerns regarding the authenticity of the images we see every day on the Internet. However, th…
Towards generalisable and calibrated synthetic speech detection with self-supervised representations
Octavian Pascu, Adriana Stan, Dan Oneata +2
Generalisation -- the ability of a model to perform well on unseen data -- is crucial for building reliable deepfake detectors. However, recent studies have shown that the current…
Visually grounded few-shot word learning in low-resource settings
Leanne Nortje, Dan Oneata, Herman Kamper
We propose a visually grounded speech model that learns new words and their visual depictions from just a few word-image example pairs. Given a set of test images and a spoken quer…
Multilingual Multimodal Learning with Machine Translated Text
Chen Qiu, Dan Oneata, Emanuele Bugliarello +2
Most vision-and-language pretraining research focuses on English tasks. However, the creation of multilingual multimodal evaluation datasets (e.g. Multi30K, xGQA, XVNLI, and MaRVL)…
YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
Kayode Olaleye, Dan Oneata, Herman Kamper
Visually grounded speech (VGS) models are trained on images paired with unlabelled spoken captions. Such models could be used to build speech systems in settings where it is imposs…
FlexLip: A Controllable Text-to-Lip System
Dan Oneata, Beata Lorincz, Adriana Stan +1
The task of converting text input into video content is becoming an important topic for synthetic media generation. Several methods have been proposed with some of them reaching cl…
Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations
Dan Oneata, Horia Cucu
Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated t…
Keyword localisation in untranscribed speech using visually grounded speech models
Kayode Olaleye, Dan Oneata, Herman Kamper
Keyword localisation is the task of finding where in a speech utterance a given query keyword occurs. We investigate to what extent keyword localisation is possible using a visuall…
Speaker disentanglement in video-to-speech conversion
Dan Oneata, Adriana Stan, Horia Cucu
The task of video-to-speech aims to translate silent video of lip movement to its corresponding audio signal. Previous approaches to this task are generally limited to the case of…