Comparison of Self-Supervised Speech Pre-Training Methods for Flemish Dutch ASR Inference Efficiency

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: How do different self-supervised speech pre-training methods (e.g., wav2vec 2.0, HuBERT, Data2Vec) compare in inference efficiency (real-time factor) when fine-tuned on Flemish Dutch ASR tasks using identical downstream architectures?

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