AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

VocSim A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

Maris Basha, Anja T Zai, Sabine Stoll, Richard Hahnloser

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add transductive PCA (D100) (ablation)Whisper-L-v3 EWMTF · VocSim public setsP@1 (%): 61.5 -> 66.8Improved
add transductive PCA (D100) (ablation)CLAP · VocSim public setsP@1 (%): 61.7 -> 63.7Improved
add transductive PCA (D100) (ablation)WavLM-Large · VocSim public setsP@1 (%): 62.8 -> 64.1Improved
add transductive PCA (D100) (ablation)Whisper-L-v3 · VocSim blind setsP@1 (%): 11.5 -> 11.5No clear effect
use Whisper-Large-v3 instead of Whisper-Small (ablation)Whisper · VocSim public setsP@1 (%): 57.4 -> 66.8Improved
use Whisper-Large-v3 instead of Whisper-Small (ablation)Whisper · VocSim public setsGSR (%): 28.7 -> 41.7Improved
use Whisper-Large-v3 instead of Whisper-Small (ablation)Whisper · VocSim blind setsP@1 (%): 5.7 -> 11.5Improved
use Whisper-Large-v3 instead of Whisper-Small (ablation)Whisper · VocSim blind setsGSR (%): 29.1 -> 39.4Improved
include padding tokens in mean pooling instead of masking (ablation)Whisper encoder · BC subsetP@1 (%): 41.1% -> 65.5%Improved
add DTW re-ranking to statistical pooling (ablation)Whisper pipeline · VocSimP@1 and GSRNo clear effect
flip 1-20% of labels (ablation)GSR metric · VocSimP@1 and GSRHurt
vary encoder layer across all 32 layers (ablation)Whisper encoder · VocSimP@1 / GSRNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy