Related papers: Comprehensive Layer-wise Analysis of SSL Models fo…
Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained…
Audio deepfake model attribution aims to mitigate the misuse of synthetic speech by identifying the source model responsible for generating a given audio sample, enabling accountability and informing vendors. The task is challenging, but…
Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…
Enhancing explainability in speech self-supervised learning (SSL) is important for developing reliable SSL-based speech processing systems. This study probes how speech SSL models encode speaker-specific information via a large-scale…
Recent progress in generative AI has made it increasingly easy to create natural-sounding deepfake speech from just a few seconds of audio. While these tools support helpful applications, they also raise serious concerns by making it…
Audio deepfake detection systems based on frozen pre-trained self-supervised learning (SSL) encoders show a high level of performance when combined with layer-weighted pooling methods, such as multi-head factorized attentive pooling (MHFA).…
The SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-supervised learning…
Recently, pre-trained models for music information retrieval based on self-supervised learning (SSL) are becoming popular, showing success in various downstream tasks. However, there is limited research on the specific meanings of the…
The state-of-the-art audio deepfake detectors leveraging deep neural networks exhibit impressive recognition performance. Nonetheless, this advantage is accompanied by a significant carbon footprint. This is mainly due to the use of…
Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training to encode general-purpose representations. In contrast,…
Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals.…
Automatic singing voice understanding tasks, such as singer identification, singing voice transcription, and singing technique classification, benefit from data-driven approaches that utilize deep learning techniques. These approaches work…
Recent advances in synthetic speech have made audio deepfakes increasingly realistic, posing significant security risks. Existing detection methods that rely on a single modality, either raw waveform embeddings or spectral based features,…
Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…
In this paper, we propose a deep-learning framework for environmental sound deepfake detection (ESDD) -- the task of identifying whether the sound scene and sound event in an input audio recording is fake or not. To this end, we conducted…
The rapid development of audio-driven talking head generators and advanced Text-To-Speech (TTS) models has led to more sophisticated temporal deepfakes. These advances highlight the need for robust methods capable of detecting and…
Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…
Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techniques for detecting audio spoofs, it is often unclear exactly…
Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated…
Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…