VRM-Phase I VKW system description of long-short video customizable keyword wakeup challenge

TL;DR

This paper describes the VKW challenge for building flexible Chinese video keyword wakeup systems capable of handling multiple and custom keywords, with experimental results from participating teams.

Contribution

It introduces a new public dataset and evaluation framework for Chinese video keyword wakeup, fostering research in customizable wakeup systems.

Findings

Participating systems support multiple keywords.

Systems can wake up on custom keywords.

Experimental results demonstrate system effectiveness.

Abstract

Keyword wakeup technology has always been a research hotspot in speech processing, but many related works were done on different datasets. We organized a Chinese long-short video keyword wakeup challenge (Video Keyword Wakeup Challenge, VKW) for testing the ability of each participating team to build a keyword wakeup system under the public dataset. All submitted systems not only need to support the setting of multiple different keywords, but also need to support the wakeup of any costumed keyword.This paper mainly describes the basic situation of the VKW challenge and the experimental results of some participating teams.