“Oh, I’ve Heard That Before”: Modelling Own-Dialect Bias After Perceptual Learning by Weighting Training Data

Rachael Tatman


Abstract
Human listeners are able to quickly and robustly adapt to new accents and do so by using information about speaker’s identities. This paper will present experimental evidence that, even considering information about speaker’s identities, listeners retain a strong bias towards the acoustics of their own dialect after dialect learning. Participants’ behaviour was accurately mimicked by a classifier which was trained on more cases from the base dialect and fewer from the target dialect. This suggests that imbalanced training data may result in automatic speech recognition errors consistent with those of speakers from populations over-represented in the training data.
Anthology ID:
W17-0704
Volume:
Proceedings of the 7th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2017)
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Ted Gibson, Tal Linzen, Asad Sayeed, Martin van Schijndel, William Schuler
Venue:
CMCL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
29–34
Language:
URL:
https://aclanthology.org/W17-0704
DOI:
10.18653/v1/W17-0704
Bibkey:
Cite (ACL):
Rachael Tatman. 2017. “Oh, I’ve Heard That Before”: Modelling Own-Dialect Bias After Perceptual Learning by Weighting Training Data. In Proceedings of the 7th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2017), pages 29–34, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
“Oh, I’ve Heard That Before”: Modelling Own-Dialect Bias After Perceptual Learning by Weighting Training Data (Tatman, CMCL 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-0704.pdf