Noise-Robust Keyword Spotting through Self-supervised Pretraining

arXiv:2403.18560v1 Announce Type: cross
Abstract: Voice assistants are now widely available, and to activate them a keyword spotting (KWS) algorithm is used. Modern KWS systems are mainly trained using supervised learning methods and require a large amount of labelled data to achieve a good performance. Leveraging unlabelled data through self-supervised learning (SSL) has been shown to increase the accuracy in clean conditions. This paper explores how SSL pretraining such as Data2Vec can be used to enhance the robustness of KWS …

abstract algorithm arxiv assistants cs.lg cs.sd data eess.as good modern noise performance pretraining robust self-supervised learning ssl supervised learning systems them through type voice voice assistants