AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer

Jianwei Zhang, Suren Jayasuriya, Visar Berisha

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 0 citations (OpenAlex)

Read the paper

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 ICC regularizer to GE2E loss (ablation)VGG-M-40 · VoxCeleb1 TI-SVEER: 4.39% -> 3.96%Improved
add ICC regularizer to GE2E loss (ablation)FastResNet-34 · VoxCeleb1 TI-SVEER: 2.49% -> 2.39%Improved
add ICC regularizer to AngleProto loss (ablation)VGG-M-40 · VoxCeleb1 TI-SVEER: 4.36% -> 4.02%Improved
add ICC regularizer to AngleProto loss (ablation)FastResNet-34 · VoxCeleb1 TI-SVEER: 2.28% -> 2.17%Improved
add ICC regularizer to SupCon loss (ablation)VGG-M-40 · VoxCeleb1 TI-SVEER: 3.91% -> 3.78%Improved
add ICC regularizer to GE2E loss (ablation)VGG-M-40 · VoxCeleb1 TI-SVICC: 0.4494 -> 0.5487Improved
add ICC regularizer to GE2E loss (ablation)FastResNet-34 · VoxCeleb1 TI-SVICC: 0.7215 -> 0.7366Improved
add ICC regularizer to SupCon loss (ablation)VGG-M-40 · VoxCeleb1 TI-SVminDCF: 0.2791 -> 0.2597Improved
add ICC regularizer to AngleProto loss (ablation)VGG-M-40 · VoxCeleb1 TI-SVminDCF: 0.2809 -> 0.2790No clear effect
train AutoVC with GE2E+ICC speaker embeddingsAutoVC · VCTK zero-shot conversion AB testselection ratio: 38.10% -> 61.90%Improved
train AutoVC with GE2E+ICC speaker embeddingsAutoVC · VCTK zero-shot conversionWER: 0.5810 -> 0.5109Improved
train AutoVC with GE2E+ICC speaker embeddingsAutoVC · VCTK zero-shot conversionspeaker similarity: 0.2231 -> 0.2309Improved

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