Exploring Data Augmentation in Bias Mitigation Against Non-Native-Accented Speech

Conference Paper (2023)
Author(s)

Y. Zhang (TU Delft - Multimedia Computing)

Aaricia Herygers (External organisation)

T.B. Patel (TU Delft - Multimedia Computing)

Z. Yue (TU Delft - Multimedia Computing)

Odette Scharenborg (TU Delft - Multimedia Computing)

Multimedia Computing
Copyright
© 2023 Y. Zhang, Aaricia Herygers, T.B. Patel, Z. Yue, O.E. Scharenborg
DOI related publication
https://doi.org/10.1109/ASRU57964.2023.10389756
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Y. Zhang, Aaricia Herygers, T.B. Patel, Z. Yue, O.E. Scharenborg
Multimedia Computing
ISBN (print)
979-8-3503-0690-3
ISBN (electronic)
979-8-3503-0689-7
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Automatic speech recognition (ASR) should serve every speaker, not only the majority “standard” speakers of a language. In order to build inclusive ASR, mitigating the bias against speaker groups who speak in a “non-standard” or “diverse” way is crucial. We aim to mitigate the bias against non-native-accented Flemish in a Flemish ASR system. Since this is a low-resource problem, we investigate the optimal type of data augmentation, i.e., speed/pitch perturbation, cross-lingual voice conversion-based methods, and SpecAugment, applied to both native Flemish and non-native-accented Flemish, for bias mitigation. The results showed that specific types of data augmentation applied to both native and non-native-accented speech improve non-native-accented ASR while applying data augmentation to the non-native-accented speech is more conducive to bias reduction. Combining both gave the largest bias reduction for human-machine interaction (HMI) as well as read-type speech.

Files

Exploring_Data_Augmentation_in... (pdf)
(pdf | 0.511 Mb)
- Embargo expired in 19-07-2024
License info not available