mlsanityData to 14 Oct 2026

Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR

arXiv 2610.13432 ↗First posted 9 Oct 2026eess.AS cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Earnings call transcription presents a realistic continual learning scenario where Automatic Speech Recognition (ASR) systems are updated with new recordings but risk catastrophic forgetting of previously learned financial speech patterns. Adapting Whisper-small from a general-domain speech corpus to the Earnings22 benchmark reveals the opposite: all evaluated methods exhibit improvement on held-out financial speech from the same domain during adaptation rather than forgetting. This task complementarity makes regularization counterproductive. Nevertheless, when regularization is warranted, a layer-wise mini-Kronecker-Factored Approximate Curvature (mini-KFAC) approximation seems to achieve lower word error rates (WERs) and more stable optimization than standard diagonal Elastic Weight Consolidation (EWC). The results suggest that task complementarity should be assessed before applying continual learning constraints, and prefer mini-KFAC EWC over diagonal EWC when needed.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

12 of 18 references.

References · 12

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  4. 2016Progressive Neural Networkscited by 1,361
  5. 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 796
  6. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  7. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 62
  8. 2022Earnings-22: A Practical Benchmark for Accents in the Wildcited by 50
  9. 2019Statistical Testing on ASR Performance via Blockwise Bootstrapcited by 4
  10. 2021Kronecker Factorization for Preventing Catastrophic Forgetting in Large-scale Medical Entity Linkingcited by 1
  11. 2023Continual Learning for End-to-End ASR by Averaging Domain Expertscited by 1
  12. 2025Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligencecited by 1

Built on by

Not cited yet.