Kate M. Knill

It is demonstrated that articulatory representations created through articulatory inversion can be used as an interpretable basis for accent comparison and that optimal transport provides a framework for accent comparison across arbitrary recording types.

Transforming written L2 responses into spoken-style transcripts can dramatically enhance the accuracy of automated speaking assessments.

LLMs aren't equally reliable as NLG evaluators, but a Bradley-Terry extension called BT-sigma can learn judge reliability from pairwise comparisons alone, improving ranking accuracy without human supervision.