Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations

arXiv:2609.34030 · cs.SD, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.SD, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Project page: https://sites.google

Terminology

• Model-Agnostic — 4× in this paper · explained in 2 episodes
• Interpretability — 3× in this paper · explained in 15 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Concept Alignment Score — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Ensemble Approach — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Random Forest — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Qwen2 Technical Report

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs