Ensemble of learning in Self-supervised speech recognition Poster presented at the Deep Learning Indaba 2023 by Ussen Kimanuka
Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide pathways to large vocabular
Automatic Speech Recognition (ASR) systems have become a very natural human-machine interaction in w
While many speakers of low-resource languages regularly code-switch between their languages and othe
Automatic speech recognition (ASR) is crucial for human-machine interaction in diverse applications
International audience This paper investigates the potential of improving a hybrid au