TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/VoxCeleb1

VoxCeleb1

AudioIntroduced 2017-06-26

VoxCeleb1 is an audio dataset containing over 100,000 utterances for 1,251 celebrities, extracted from videos uploaded to YouTube.

Benchmarks

Few-Shot Learning/Top-1 Accuracy(5-Way-1-Shot)Meta-Learning/Top-1 Accuracy(5-Way-1-Shot)Speaker Identification/Top-1 (%)Speaker Identification/Top-5 (%)Speaker Identification/Number of ParamsSpeaker Identification/AccuracySpeaker Recognition/EERSpeaker Verification/EER

Related Benchmarks

VoxCeleb1 - 1-shot learning/10-shot image generation/FIDVoxCeleb1 - 1-shot learning/3D/FIDVoxCeleb1 - 1-shot learning/3D Face Modelling/FIDVoxCeleb1 - 1-shot learning/3D Face Reconstruction/FIDVoxCeleb1 - 1-shot learning/Face Generation/FIDVoxCeleb1 - 1-shot learning/Face Reconstruction/FIDVoxCeleb1 - 1-shot learning/Facial Recognition and Modelling/FIDVoxCeleb1 - 1-shot learning/Image Generation/FIDVoxCeleb1 - 1-shot learning/Talking Head Generation/FIDVoxCeleb1 - 32-shot learning/10-shot image generation/FIDVoxCeleb1 - 32-shot learning/3D/FIDVoxCeleb1 - 32-shot learning/3D Face Modelling/FIDVoxCeleb1 - 32-shot learning/3D Face Reconstruction/FIDVoxCeleb1 - 32-shot learning/Face Generation/FIDVoxCeleb1 - 32-shot learning/Face Reconstruction/FIDVoxCeleb1 - 32-shot learning/Facial Recognition and Modelling/FIDVoxCeleb1 - 32-shot learning/Image Generation/FIDVoxCeleb1 - 32-shot learning/Talking Head Generation/FIDVoxCeleb1 - 8-shot learning/10-shot image generation/FIDVoxCeleb1 - 8-shot learning/3D/FIDVoxCeleb1 - 8-shot learning/3D Face Modelling/FIDVoxCeleb1 - 8-shot learning/3D Face Reconstruction/FIDVoxCeleb1 - 8-shot learning/Face Generation/FIDVoxCeleb1 - 8-shot learning/Face Reconstruction/FIDVoxCeleb1 - 8-shot learning/Facial Recognition and Modelling/FIDVoxCeleb1 - 8-shot learning/Image Generation/FIDVoxCeleb1 - 8-shot learning/Talking Head Generation/FID

Statistics

Papers
680
Benchmarks
8

Links

Homepage

Tasks

Few-Shot Audio ClassificationFew-Shot LearningLearning with noisy labelsMeta-LearningSpeaker IdentificationSpeaker RecognitionSpeaker VerificationTalking Head GenerationVideo Reconstruction