金融语音是否需要持续学习正则化？对EWC和mini-KFAC在财报电话会议ASR上的研究
Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR
AI总结：
该研究针对财报电话会议ASR场景，发现任务互补性使持续学习正则化适得其反，需正则化时mini-KFAC EWC比对角EWC性能更优。
摘要：
财报电话会议转录呈现了一个现实的持续学习场景：自动语音识别（ASR）系统会随着新录音更新，但存在灾难性遗忘已学习的金融语音模式的风险。将通用领域语音语料库的Whisper-small适配到Earnings22基准后，结果却相反：所有评估方法在适配期间对同一领域的保留金融语音均表现出性能提升，而非遗忘。这种任务互补性使得正则化适得其反。不过，当需要正则化时，分层的mini-Kronecker-Factored近似曲率（mini-KFAC）相比标准的对角弹性权重整合（EWC），词错误率（WER）更低且优化更稳定。研究结果表明，应用持续学习约束前应评估任务互补性，必要时优先选择mini-KFAC EWC而非对角EWC。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
