Auto-KWS 2021 challenge: Task, datasets, and baselines

Wang，Jingsong1; He，Yuxuan1; Zhao，Chunyu1; Shao，Qijie2; Tu，Wei Wei1,3; Ko，Tom4; Lee，Hung Yi5; Xie，Lei2

10.21437/Interspeech.2021-817

2021

2308-457X

1990-9772

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

6

4041-4045

Auto-KWS 2021 challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to a customized keyword spotting task. Compared with other keyword spotting tasks, Auto-KWS challenge has the following three characteristics: 1) The challenge focuses on the problem of customized keyword spotting, where the target device can only be awakened by an enrolled speaker with his/her specified keyword. The speaker can use any language and accent to define his keyword. 2) All data of the challenge is recorded in realistic environment to simulate different user scenarios. 3) Auto-KWS is a "code competition", where participants need to submit AutoML solutions, then the platform automatically runs the enrollment and prediction steps with the submitted code. This challenge aims at promoting the development of a more personalized and flexible keyword spotting system. Two baseline systems are provided to all participants as references.

Auto-KWS Automated deep learning Automated machine learning AutoSpeech Keyword spotting Meta-learning Query by example

通讯

英语

EI

20214711194610

Deep learning ; Speech communication

Ergonomics and Human Factors Engineering:461.4 ; Automatic Control Principles and Applications:731 ; Speech:751.5

2-s2.0-85119281254

Scopus

1.4Paradigm Inc.,China
2.ASLP@NPU,Northwestern Polytechnical University,China
3.ChaLearn,United States
4.Department of Computer Science and Engineering,Southern University of Science and Technology,China
5.College of Electrical Engineering and Computer Science,National Taiwan University,Taiwan

Wang，Jingsong,He，Yuxuan,Zhao，Chunyu,et al. Auto-KWS 2021 challenge: Task, datasets, and baselines[C],2021:4041-4045.