Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Similar to humans' cognitive ability to generalize knowledge and skills, self-supervised
learning (SSL) targets discovering general representations from large-scale data. This …

Mainstream machine listening models are trained to learn audio concepts under the
paradigm of one class label to many recordings focusing on one task. Learning under such …

In the domain of audio processing, Transfer Learning has facilitated the rise of Self-
Supervised Learning and Zero-Shot Learning techniques. These approaches have led to …

Recent general-purpose audio representations show state-of-the-art performance on
various audio tasks. These representations are pre-trained by self-supervised learning …

In this paper, we focus on Whisper, a recent automatic speech recognition model trained
with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first …

Automated bioacoustic analysis aids understanding and protection of both marine and
terrestrial animals and their habitats across extensive spatiotemporal scales, and typically …

Automatic detection and classification of animal sounds has many applications in
biodiversity monitoring and animal behavior. In the past twenty years, the volume of digitised …

Pre-trained models are essential as feature extractors in modern machine learning systems
in various domains. In this study, we hypothesize that representations effective for general …

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image
generation and fiction co-creation, AI for music remains relatively nascent, particularly in …