AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition

Martijn Bartelds, Ananjan Nandi, Moussa Koulako Bala Doumbouya, Dan Jurafsky, Tatsunori Hashimoto, Karen Livescu

ICLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use CTC-DRO instead of baseline fine-tuningMMS/XLS-R multilingual ASR · ML-SUPERB 2.0 sets 1-5worst-language CER: 90.0 -> 57.5 (MMS, set 5); 114.8 -> 71.5 (XLS-R, set 5)Improved
use CTC-DRO instead of baseline fine-tuningMMS/XLS-R · ML-SUPERB 2.0 sets 1-5average CER: 25.2 -> 22.5 (XLS-R set 1); 29.9 -> 23.8 (XLS-R set 5)Improved
use original Group DRO instead of baselineMMS/XLS-R · ML-SUPERB 2.0 sets 1-5average CER: 23.4 -> 30.5 (MMS set 1)Hurt
use original Group DRO instead of baselineMMS/XLS-R · ML-SUPERB 2.0worst-language CER: 60.8 -> 86.6 (MMS set 1); 90.0 -> 62.2 (MMS set 5)Mixed
add length-matched group losses to CTC-DRO (ablation)CTC-DRO XLS-R · Set 5worst-language CER: 115.2 -> 71.5Improved
add smoothed maximization objective to CTC-DRO (ablation)CTC-DRO XLS-R · Set 5worst-language CER: 194.2 -> 71.5Improved
add length-matched group losses to CTC-DRO (ablation)CTC-DRO MMS · Set 5average CER: 29.5 -> 24.3Improved
add smoothed maximization objective to CTC-DRO (ablation)CTC-DRO MMS · Set 5average CER: 97.9 -> 24.3Improved
add additional unbalanced training data, CTC-DRO vs baselineXLS-R · Set 2 (additional data)worst-language CER: 97.2 -> 51.4Improved
scale to 18 languagesCTC-DRO · 18-language set (balanced)worst-language CER: 8.9% (MMS), 9.2% (XLS-R) relative reductionImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy