arXiv:2607. 03806v1 Announce Type: cross Abstract: Audio foundation models are widely adopted as general-purpose feature extractors, yet the internal structure of their learned representations remains insufficiently understood.
arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.
arXiv:2608. 14819v1 Announce Type: cross Abstract: Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic.
arXiv:2607. 08545v1 Announce Type: cross Abstract: End-to-end neural audio models achieve high-fidelity compression and generation.
arXiv:2603. 27218v2 Announce Type: replace-cross Abstract: Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces.
arXiv:2603. 23667v2 Announce Type: replace-cross Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions.
arXiv:2607. 27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes.
arXiv:2607. 24786v1 Announce Type: cross Abstract: Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale.
arXiv:2608. 15037v1 Announce Type: cross Abstract: Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference.
arXiv:2606. 18273v1 Announce Type: cross Abstract: Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis.
arXiv:2606. 25225v1 Announce Type: cross Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning.
Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes. However, these methods often disregard dependencies between notes, which poses a potential limitation in assessing the similarity between two sets of performances.
arXiv:2606. 14662v1 Announce Type: new Abstract: Pretrained audio embeddings are standard in bioacoustics, yet little is known about which acoustic features these models encode, nor which are useful for a given task.