SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting

TL;DR

SLiCK introduces a length-constrained keyword spotting method that leverages subsequences and multi-task learning to improve accuracy on resource-limited devices, effectively distinguishing similar keywords.

Contribution

The paper presents a novel length-constrained approach for keyword spotting using subsequences and a multi-task training scheme, enhancing performance over existing methods.

Findings

Increased AUC from 88.52 to 94.9 on Libriphrase hard dataset.

Reduced EER from 18.82 to 11.1, demonstrating improved accuracy.

Effective differentiation of similar-sounding keywords through subsequence-level matching.

Abstract

User-defined keyword spotting on a resource-constrained edge device is challenging. However, keywords are often bounded by a maximum keyword length, which has been largely under-leveraged in prior works. Our analysis of keyword-length distribution shows that user-defined keyword spotting can be treated as a length-constrained problem, eliminating the need for aggregation over variable text length. This leads to our proposed method for efficient keyword spotting, SLiCK (exploiting Subsequences for Length-Constrained Keyword spotting). We further introduce a subsequence-level matching scheme to learn audio-text relations at a finer granularity, thus distinguishing similar-sounding keywords more effectively through enhanced context. In SLiCK, the model is trained with a multi-task learning approach using two modules: Matcher (utterance-level matching task, novel subsequence-level matching task) and Encoder (phoneme recognition task). The proposed method improves the baseline results on Libriphrase hard dataset, increasing AUC from $88.52$ to $94.9$ and reducing EER from $18.82$ to $11.1$.