Dutch

The 'Dutch' dataset/benchmark contains data used for multilingual fine-tuning in Automatic Speech Recognition (ASR) systems, specifically to evaluate and improve performance for Frisian and its regional dialects.

Papers using Dutch (3)

Word stress in self-supervised speech models: A cross-linguistic comparison2025 · 2 citesUtterance-Level Methods for Identifying Reliable ASR-Output for Child Speech2026Evaluating Standard And Dialectal Frisian ASR: Multilingual Fine-tuning And Language Identification For Improved Low-resource Performance2025