Vox-1-H

The 'Vox-1-H' dataset is a benchmark used to evaluate speaker verification performance, specifically measuring the effectiveness of models in distinguishing between different speakers.

Papers using Vox-1-H (4)

Enhancing 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-Spoofing2025An 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 adapters2022