Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech

  • Katrin Tomanek
  • , Vicky Zayats
  • , Dirk Padfield
  • , Kara Vaillancourt
  • , Fadi Biadsy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

42 Scopus citations

Abstract

Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has previously been shown that personalization through model fine-tuning substantially improves performance. However, maintaining such large models per speaker is costly and difficult to scale. We show that by adding a relatively small number of extra parameters to the encoder layers via so-called residual adapter, we can achieve similar adaptation gains compared to model fine-tuning, while only updating a tiny fraction (less than 0.5%) of the model parameters. We demonstrate this on two speech adaptation tasks (atypical and accented speech) and for two state-of-the-art ASR architectures.

Original languageEnglish
Title of host publicationEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages6751-6760
Number of pages10
ISBN (Electronic)9781955917094
DOIs
StatePublished - 1 Jan 2021
Externally publishedYes
Event2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 - Hybrid, Punta Cana, Dominican Republic
Duration: 7 Nov 202111 Nov 2021

Publication series

NameEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Country/TerritoryDominican Republic
CityHybrid, Punta Cana
Period7/11/2111/11/21

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech'. Together they form a unique fingerprint.

Cite this