On Dutch end-to-end ASR systems, average word error rate hides large performance gaps across speaker groups, and bias mitigation can lower the average while increasing bias.
The Dutch Corpora We use the Corpus Gesproken Nederlands (CGN) [38], which consists of speech spoken by Dutch adult, native speakers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How to Evaluate Automatic Speech Recognition: Comparing Different Performance and Bias Measures
On Dutch end-to-end ASR systems, average word error rate hides large performance gaps across speaker groups, and bias mitigation can lower the average while increasing bias.