AudioSet
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
BAT: Better Audio Transformer Guided by Convex Gated Probing
arXiv:2602.16305v2 Announce Type: replace Abstract: Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as finetuning may misrepresent their inherent quality. In contrast, audio SSL models still rely on finetuning because simple probing fails to unlock their full potential and alters their rankings when competing on AudioSet. Hence, a robust and efficient probing mechanism is required to guide the trajectory of audio SSL towards...
Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Announce Type: replace Abstract: Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursuing state-of-the-art on AudioSet. A key reason is that global pooling creates an information bottleneck causing linear probes to misrepresent the embedding quality: The $\texttt{cls}$-token discards crucial token information about dispersed, localized events in audio. This weakness is rooted in the mismatch between the...
Sound Event Detection with Boundary-Aware Optimization and Inference
arXiv:2601.04178v2 Announce Type: replace-cross Abstract: Temporal detection problems appear in many fields including time-series estimation, activity recognition and sound event detection (SED). In this work, we propose a new approach to temporal event modeling by explicitly modeling event onsets and offsets, and by introducing boundary-aware optimization and inference strategies that substantially enhance temporal event detection. The presented methodology incorporates new temporal...
Sound Effects Dataset Unification With the Universal Category System
Announce Type: new Abstract: Sound effects (SFX) datasets and libraries often employ distinct tagging schemes, taxonomies, and metadata structures. This creates challenges for research on SFX classification and generation because incompatible taxonomies lead to siloed datasets that might require individualized approaches, result in non-comparable outcomes, and prevent data merging strategies. We propose a modular dataset relabeling framework that adopts the Universal Category System (UCS),...