**Domain-specific fine-tuning effects on Flemish Dutch self-supervised WER performance**

Recent research in speech processing exhibits a growing interest in unsupervised and self-supervised representation learning from unlabelled data to alleviate the need for large amounts of annotated data. We investigate several popular pre-training methods and apply them to Flemish Dutch. We compare off-the-shelf English pre-trained models to models trained on an increasing amount of Flemish data. We find that the most important factors for positive transfer to downstream speech recognition tasks include a substantial amount of data and a matching pre-training domain. Ideally, we also finetune

Research goal: What is the impact of domain-specific fine-tuning (e.g., conversational vs. broadcast speech) on the Word Error Rate (WER) performance of Flemish Dutch self-supervised models compared to English pre-trained models?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.