@inproceedings{d082c3402e89465eb3900290d897c02f,
title = "Wekws: A Production First Small-Footprint End-to-End Keyword Spotting Toolkit",
abstract = "Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have be-come the most popular approach for on-device KWS tasks. However, there is still a gap between the research and deployment of E2E KWS methods. In this paper, we introduce WeKws, a production-quality, easy-to-build, and convenient-to-be-applied E2E KWS toolkit. WeKws contains the implementations of several state-of-the-art backbone networks, making it achieve highly competitive results on three publicly available datasets. To make WeKws a pure E2E toolkit, we utilize a refined max-pooling loss to make the model learn the ending position of the keyword by itself, which significantly simplifies the training pipeline and makes WeKws very efficient to be applied in real-world scenarios. The toolkit is publicly available at https://github.com/wenet-e2e/wekws.",
keywords = "end-to-end, production first, spotting",
author = "Jie Wang and Menglong Xu and Jingyong Hou and Binbin Zhang and Zhang, {Xiao Lei} and Lei Xie and Fuping Pan",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",
year = "2023",
doi = "10.1109/ICASSP49357.2023.10096736",
language = "英语",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
}