KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods

arXiv:2308.11863v3 Announce Type: replace-cross
Abstract: Despite recent availability of large transcribed Kinyarwanda speech data, achieving robust speech recognition for Kinyarwanda is still challenging. In this work, we show that using self-supervised pre-training, following a simple curriculum schedule during fine-tuning and using semi-supervised learning to leverage large unlabelled speech data significantly improve speech recognition performance for Kinyarwanda. Our approach focuses on using public domain data only. A new studio-quality speech dataset is collected from a public website, then used to train …

abstract arxiv availability cs.lg cs.sd curriculum data eess.as fine-tuning pre-training recognition robust semi-supervised semi-supervised learning show simple speech speech recognition supervised learning training type via work