Related papers: Towards Pre-training an Effective Respiratory Audi…

We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations.…

To reduce the need for skilled clinicians in heart sound interpretation, recent studies on automating cardiac auscultation have explored deep learning approaches. However, despite the demands for large data for deep learning, the size of…

Deep audio classification, traditionally cast as training a deep neural network on top of mel-filterbanks in a supervised fashion, has recently benefited from two independent lines of work. The first one explores "learnable frontends",…

Speech foundation models have demonstrated exceptional capabilities in speech-related tasks. Nevertheless, these models often struggle with non-verbal audio data, such as vocalizations, baby crying, etc., which are critical for various…

Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if…

Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domains. While AudioSet is a pivotal step to bridge this gap as a…

As deepfake audio becomes more realistic and diverse, developing generalizable countermeasure systems has become crucial. Existing detection methods primarily depend on XLS-R front-end features to improve generalization. Nonetheless, their…

Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to…

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we…

Recent advances in foundation models have enabled audio-generative models that produce high-fidelity sounds associated with music, events, and human actions. Despite the success achieved in modern audio-generative models, the conventional…

As the burden of respiratory diseases continues to fall on society worldwide, this paper proposes a high-quality and reliable dataset of human sounds for studying respiratory illnesses, including pneumonia and COVID-19. It consists of…

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons…

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…

The advent of hyper-scale and general-purpose pre-trained models is shifting the paradigm of building task-specific models for target tasks. In the field of audio research, task-agnostic pre-trained models with high transferability and…

Language models are typically trained on large corpora of text in their default orthographic form. However, this is not the only option; representing data as streams of phonemes can offer unique advantages, from deeper insights into…

Transfer learning is commonly employed to leverage large, pre-trained models and perform fine-tuning for downstream tasks. The most prevalent pre-trained models are initially trained using ImageNet. However, their ability to generalize can…

Audio tagging is an active research area and has a wide range of applications. Since the release of AudioSet, great progress has been made in advancing model performance, which mostly comes from the development of novel model architectures…

Generalization is a main issue for current audio deepfake detectors, which struggle to provide reliable results on out-of-distribution data. Given the speed at which more and more accurate synthesis methods are developed, it is very…

Remote screening of respiratory diseases has been widely studied as a non-invasive and early instrument for diagnosis purposes, especially in the pandemic. The respiratory sound classification task has been realized with numerous deep…

Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high…