Vox-1-O

The 'Vox1-O' dataset is a benchmark used to evaluate speaker verification performance, specifically measuring the equal error rate (EER) of models in identifying speakers.

Papers using Vox-1-O (8)

An Attention-based Backend Allowing Efficient Fine-tuning Of Transformer Models For Speaker Verification2022 · 30 citesEnhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning2025Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing2025Espnet-spk: Full Pipeline Speaker Embedding Toolkit With Reproducible Recipes, Self-supervised Front-ends, And Off-the-shelf Models2024 · 21 citesPCF: ECAPA-TDNN with Progressive Channel Fusion for Speaker Verification2023 · 1 citesAn attention-based backend allowing efficient fine-tuning of transformer models for speaker verification2022Parameter-efficient transfer learning of pre-trained Transformer models for speaker verification using adapters2022ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models2024