Towards inclusive automatic speech recognition

Siyuan Feng, Bence Mark Halpern, Olya Kudina, Odette Scharenborg*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

3 Citations (Scopus)
89 Downloads (Pure)

Abstract

Practice and recent evidence show that state-of-the-art (SotA) automatic speech recognition (ASR) systems do not perform equally well for all speaker groups. Many factors can cause this bias against different speaker groups. This paper, for the first time, systematically quantifies and finds speech recognition bias against gender, age, regional accents and non-native accents, and investigates the origin of this bias by investigating bias cross-lingually (i.e., Dutch and Mandarin) and for two different SotA ASR architectures (a hybrid DNN-HMM and an attention based end-to-end (E2E) model) through a phoneme error analysis. The results show that only a fraction of the bias can be explained by pronunciation differences between speaker groups, and that in order to mitigate bias, language- and architecture specific solutions need to be found.
Original languageEnglish
Article number101567
Number of pages15
JournalComputer Speech and Language
Volume84
DOIs
Publication statusPublished - 2023

Keywords

  • Accent
  • Age
  • Bias
  • Gender
  • Inclusive automatic speech recognition

Fingerprint

Dive into the research topics of 'Towards inclusive automatic speech recognition'. Together they form a unique fingerprint.

Cite this