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 …
S Deshmukh, B Elizalde, R Singh… - Advances in Neural …, 2023 - proceedings.neurips.cc
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 …
D Niizumi, D Takeuchi, Y Ohishi… - … Evaluation of Audio …, 2022 - proceedings.mlr.press
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 …
D Niizumi, D Takeuchi, Y Ohishi… - … on Audio, Speech …, 2022 - ieeexplore.ieee.org
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 …