WQ-Fusion combines Whisper and Qwen encoders with gated attention to reach 0.836 on the Interspeech 2026 Audio Encoder Capability Challenge, outperforming single-encoder baselines.
General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper describes Task 2 of the DCASE 2018 Challenge, titled "General-purpose audio tagging of Freesound content with AudioSet labels". This task was hosted on the Kaggle platform as "Freesound General-Purpose Audio Tagging Challenge". The goal of the task is to build an audio tagging system that can recognize the category of an audio clip from a subset of 41 diverse categories drawn from the AudioSet Ontology. We present the task, the dataset prepared for the competition, and a baseline system.
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
WQ-Fusion: Dynamic Gated Attention for Cross-Domain Audio Representation
WQ-Fusion combines Whisper and Qwen encoders with gated attention to reach 0.836 on the Interspeech 2026 Audio Encoder Capability Challenge, outperforming single-encoder baselines.