BBS-KWS:The Mandarin Keyword Spotting System Won the Video Keyword Wakeup Challenge

TL;DR

This paper presents BBS-KWS, a Mandarin keyword spotting system that combines a large backbone model, syllable units, and keyword biasing, achieving top results in the Video Keyword Wakeup Challenge.

Contribution

The paper introduces a novel Mandarin KWS system with a big backbone, syllable modeling, and keyword biasing, enhancing accuracy and generalization in video keyword detection.

Findings

Achieved first place in two tracks of the VKW challenge.

Significant improvements over baseline systems.

Effective semi-supervised learning on CN-Celeb dataset.

Abstract

This paper introduces the system submitted by the Yidun NISP team to the video keyword wakeup challenge. We propose a mandarin keyword spotting system (KWS) with several novel and effective improvements, including a big backbone (B) model, a keyword biasing (B) mechanism and the introduction of syllable modeling units (S). By considering this, we term the total system BBS-KWS as an abbreviation. The BBS-KWS system consists of an end-to-end automatic speech recognition (ASR) module and a KWS module. The ASR module converts speech features to text representations, which applies a big backbone network to the acoustic model and takes syllable modeling units into consideration as well. In addition, the keyword biasing mechanism is used to improve the recall rate of keywords in the ASR inference stage. The KWS module applies multiple criteria to determine the absence or presence of the keywords, such as multi-stage matching, fuzzy matching, and connectionist temporal classification (CTC) prefix score. To further improve our system, we conduct semi-supervised learning on the CN-Celeb dataset for better generalization. In the VKW task, the BBS-KWS system achieves significant gains over the baseline and won the first place in two tracks.