Generalisation gap of keyword spotters in a cross-speaker low-resource scenario

Łukasz Lepak*, Kacper Radzikowski, Robert Nowak, Karol J. Piczak

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Models for keyword spotting in continuous recordings can significantly improve the experience of navigating vast libraries of audio recordings. In this paper, we describe the development of such a keyword spotting system detecting regions of interest in Polish call centre conversations. Unfortunately, in spite of recent advancements in automatic speech recognition systems, human-level transcription accuracy reported on English benchmarks does not reflect the performance achievable in low-resource languages, such as Polish. Therefore, in this work, we shift our focus from complete speech-to-text conversion to acoustic similarity matching in the hope of reducing the demand for data annotation. As our primary approach, we evaluate Siamese and prototypical neural networks trained on several datasets of English and Polish recordings. While we obtain usable results in English, our models’ performance remains unsatisfactory when applied to Polish speech, both after mono-and cross-lingual training. This performance gap shows that generalisation with limited training resources is a significant obstacle for actual deployments in low-resource languages. As a potential countermeasure, we implement a detector using audio embeddings generated with a generic pre-trained model provided by Google. It has a much more favourable profile when applied in a cross-lingual setup to detect Polish audio patterns. Nevertheless, despite these promising results, its performance on out-of-distribution data are still far from stellar. It would indicate that, in spite of the richness of internal representations created by more generic models, such speech embeddings are not entirely malleable to cross-language transfer.

Original languageEnglish
Article number8313
Issue number24
Publication statusPublished - 2021 Dec 1


  • Automatic speech recognition
  • Siamese networks
  • Speech embedding
  • Spotting

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering


Dive into the research topics of 'Generalisation gap of keyword spotters in a cross-speaker low-resource scenario'. Together they form a unique fingerprint.

Cite this