Related papers: Hidden Echoes Survive Training in Audio To Audio G…
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…
Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data.…
Digital audio effects are widely used by audio engineers to alter the acoustic and temporal qualities of audio data. However, these effects can have a large number of parameters which can make them difficult to learn for beginners and…
We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions. Echoes comprises 3,577 tracks (110 hours of audio) spanning multiple genres…
The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…
In this paper, we present our comprehensive study aimed at enhancing the generalization capabilities of audio deepfake detection models. We investigate the performance of various pre-trained backbones, including Wav2Vec2, WavLM, and…
Audio steganography aims at concealing secret information in carrier audio with imperceptible modification on the carrier. Although previous works addressed the robustness of concealed message recovery against distortions introduced during…
Anomalous sound detection (ASD) in the wild requires robustness to distribution shifts such as unseen low-SNR input mixtures of machine and noise types. State-of-the-art systems extract embeddings from an adapted audio encoder and detect…
Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…
In audio-related creative tasks, sound designers often seek to extend and morph different sounds from their libraries. Generative audio models, capable of creating audio using examples as references, offer promising solutions. By masking…
The emergence of new spoofing attacks poses an increasing challenge to audio security. Current detection methods often falter when faced with unseen spoofing attacks. Traditional strategies, such as retraining with new data, are not always…
Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is…
Hiding messages for countless security purposes has become a highly fascinating subject nowadays. Encryption facilitates the data hiding. With the express development of technology, people tend to figure out a method capable of hiding a…
Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to…
In the audio modality, state-of-the-art watermarking methods leverage deep neural networks to allow the embedding of human-imperceptible signatures in generated audio. The ideal is to embed signatures that can be detected with high accuracy…
Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in both image and audio domains. In the rapidly evolving field…
Cross-modal representation learning allows to integrate information from different modalities into one representation. At the same time, research on generative models tends to focus on the visual domain with less emphasis on other domains,…
Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on…
Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…
This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…