English

Self-Train Before You Transcribe

Audio and Speech Processing 2024-06-21 v1 Computation and Language Machine Learning Sound

Abstract

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the adaptation of models under such domain shifts. However, self-training typically requires a collection of unlabelled target domain data. For settings where this is not practical, we investigate the benefit of performing noisy student teacher training on recordings in the test set as a test-time adaptation approach. Similarly to the dynamic evaluation approach in language modelling, this enables the transfer of information across utterance boundaries and functions as a method of domain adaptation. A range of in-domain and out-of-domain datasets are used for experiments demonstrating large relative gains of up to 32.2%. Interestingly, our method showed larger gains than the typical self-training setup that utilises separate adaptation data.

Keywords

Cite

@article{arxiv.2406.12937,
  title  = {Self-Train Before You Transcribe},
  author = {Robert Flynn and Anton Ragni},
  journal= {arXiv preprint arXiv:2406.12937},
  year   = {2024}
}

Comments

Accepted at Interspeech 2024

R2 v1 2026-06-28T17:10:53.950Z