BIAS in Flemish automatic speech recognition

Aaricia Herygers, Vass Verkhodanova, Matt Coler, O.E. Scharenborg, Munir Georges

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

7 Downloads (Pure)

Abstract

Research has shown that automatic speech recognition (ASR) systems exhibit biases against different speaker groups, e.g., based on age or gender. This paper presents an investigation into bias in recent Flemish ASR. Seeing as Belgian Dutch, which is also known as Flemish, is often not included in Dutch ASR systems, a state-of-the-art ASR system for Dutch is trained using the Netherlandic Dutch data from the Spoken Dutch Corpus. Using the Flemish data from the JASMIN-CGN corpus, word error rates for various regional variants of Flemish are then compared. In addition, the most misrecognized phonemes are compared across speaker groups. The evaluation confirms a bias against speakers from West Flanders and Limburg, as well as against children, male speakers, and non-native speakers.
Original languageEnglish
Title of host publicationProceedings of the ESSV Konferenz Elektronische Sprachsignalverarbeitung
Number of pages8
Publication statusPublished - 2023
EventESSV Konferenz Elektronische Sprachsignalverarbeitung - Munich, Germany
Duration: 1 Mar 20233 Mar 2023
Conference number: 34

Conference

ConferenceESSV Konferenz Elektronische Sprachsignalverarbeitung
Abbreviated titleESSV 2023
Country/TerritoryGermany
CityMunich
Period1/03/233/03/23

Fingerprint

Dive into the research topics of 'BIAS in Flemish automatic speech recognition'. Together they form a unique fingerprint.

Cite this