English

Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting

Audio and Speech Processing 2022-11-15 v1 Machine Learning Sound

Abstract

In this paper, we present a novel approach to adapt a sequence-to-sequence Transformer-Transducer ASR system to the keyword spotting (KWS) task. We achieve this by replacing the keyword in the text transcription with a special token <kw> and training the system to detect the <kw> token in an audio stream. At inference time, we create a decision function inspired by conventional KWS approaches, to make our approach more suitable for the KWS task. Furthermore, we introduce a specific keyword spotting loss by adapting the sequence-discriminative Minimum Bayes-Risk training technique. We find that our approach significantly outperforms ASR based KWS systems. When compared with a conventional keyword spotting system, our proposal has similar performance while bringing the advantages and flexibility of sequence-to-sequence training. Additionally, when combined with the conventional KWS system, our approach can improve the performance at any operation point.

Keywords

Cite

@article{arxiv.2211.06478,
  title  = {Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting},
  author = {Beltrán Labrador and Guanlong Zhao and Ignacio López Moreno and Angelo Scorza Scarpati and Liam Fowl and Quan Wang},
  journal= {arXiv preprint arXiv:2211.06478},
  year   = {2022}
}
R2 v1 2026-06-28T05:42:35.446Z