Auto-KWS 2021 challenge: Task, datasets, and baselines
Journal
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Journal Volume
6
Pages
4041-4045
Date Issued
2021
Author(s)
Abstract
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. Copyright ? 2021 ISCA.
Subjects
Auto-KWS
Automated deep learning
Automated machine learning
AutoSpeech
Keyword spotting
Meta-learning
Query by example
Deep learning
Speech communication
Autospeech
Baseline systems
Keyword spotting systems
Metalearning
Query-by example
Realistic environments
Automation
SDGs
Type
conference paper