4 papers
An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift
Peihong Zhang, Yuxuan Liu, Zhixin Li +4
Acoustic Scene Classification (ASC) faces challenges in generalizing across recording devices, particularly when labeled data is limited. The DCASE 2024 Challenge Task 1 highlights…
Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds
Jules Cauzinille, Marius Miron, Olivier Pietquin +4
Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer…
Synthetic data enables context-aware bioacoustic sound event detection
Benjamin Hoffman, David Robinson, Marius Miron +8
We propose a methodology for training foundation models that enhances their in-context learning capabilities within the domain of bioacoustic signal processing. We use syntheticall…
NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics
David Robinson, Marius Miron, Masato Hagiwara +6
Large language models (LLMs) prompted with text and audio have achieved state-of-the-art performance across various auditory tasks, including speech, music, and general audio, show…