English

Prompt-tuning in ASR systems for efficient domain-adaptation

Computation and Language 2021-10-26 v2

Abstract

Automatic Speech Recognition (ASR) systems have found their use in numerous industrial applications in very diverse domains. Since domain-specific systems perform better than their generic counterparts on in-domain evaluation, the need for memory and compute-efficient domain adaptation is obvious. Particularly, adapting parameter-heavy transformer-based language models used for rescoring ASR hypothesis is challenging. In this work, we overcome the problem using prompt-tuning, a methodology that trains a small number of domain token embedding parameters to prime a transformer-based LM to a particular domain. With just a handful of extra parameters per domain, we achieve much better perplexity scores over the baseline of using an unadapted LM. Despite being parameter-efficient, these improvements are comparable to those of fully-fine-tuned models with hundreds of millions of parameters. We replicate our findings in perplexity numbers to Word Error Rate in a domain-specific ASR system for one such domain.

Keywords

Cite

@article{arxiv.2110.06502,
  title  = {Prompt-tuning in ASR systems for efficient domain-adaptation},
  author = {Saket Dingliwal and Ashish Shenoy and Sravan Bodapati and Ankur Gandhe and Ravi Teja Gadde and Katrin Kirchhoff},
  journal= {arXiv preprint arXiv:2110.06502},
  year   = {2021}
}

Comments

WeCNLP 2021 camera-ready

R2 v1 2026-06-24T06:50:59.334Z