List your company

Audio-to-Text Retrieval on VCTK A→T

96.1Recall@1PEAV S
-3.7422.1848.174.02Dec 22, 2025

Evaluation results

MethodLinks
PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=16 Frames2025.1296.1
PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=30 FPS2025.1294.9
PEAV BA-Enc Params.=0.2B, Data (M)=124, Sampling=30 FPS2025.1294.9
PEAV BA-Enc Params.=.2B, Data (M)=124, Sampling=16 Frames2025.1294.8
PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=16 Frames2025.1285.6
PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=30 FPS2025.1285.6
PEAV L-OODA-Enc Params.=1.1B, Data (M)=114, Sampling=30 FPS, OOD=true2025.1250.7
PEAV L (PT)A-Enc Params.=1.1B, Data (M)=92, Sampling=30 FPS, PT=true2025.1216.7
ImageBindA-Enc Params.=.09B, Data (M)=32025.120.4
AFlamingo2A-Enc Params.=0.3B, Data (M)=82025.120.3
CLAP-FusionA-Enc Params.=.03B, Data (M)=32025.120.3
MS-CLAP23’A-Enc Params.=.08B, Data (M)=0.12025.120.3
CLAPA-Enc Params.=.03B, Data (M)=32025.120.2
LangBindA-Enc Params.=0.3B, Data (M)=102025.120.2
M2D-CLAPA-Enc Params.=.09B, Data (M)=22025.120.1