arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01008eess.AScs.CLcs.SD
收藏

适应关键领域:面向低资源语言的深度感知适应以实现高效的多语言语音识别

Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages

The University of Melbourne(墨尔本大学)

Yang Xiao, Eun-Jung Holden, Ting Dang

AI总结:

DAMA通过深度感知适应框架,针对不同层的适应需求优化参数,实现低资源语言高效多语言语音识别。

摘要:

最近的语音基础模型在高资源语言的多语言自动语音识别(ASR)方面表现出色,但将它们适应到低资源语言仍然具有挑战性,因为数据稀缺性和效率限制。全模型微调计算成本高且容易过拟合,而参数高效的方法如LoRA在所有层上均匀应用适应,忽略了内部表示,从而影响了效果和效率。我们分析了多语言ASR模型,并揭示出一种U形适应性模式:早期和晚期层是语言特定的,需要更多适应,而中间层保留了共享语义,需要较少适应。基于这一观察,我们提出了DAMA,一种深度感知模型适应框架,根据每层的作用分配适应能力。DAMA还引入了基于奇异值分解(SVD)的初始化来约束适应并保持U形模式,以及一个冻结的中间层基础以进一步提高效率。在两个基准数据集上评估了18种低资源语言,DAMA在80%更少的可训练参数下匹配或超过了最先进的准确性,在极端数据稀缺情况下实现了29%的误差降低,并在内存、训练时间和计算效率上显著优于基线。这些结果突显了结构感知适应在高效、可扩展的多语言ASR中的优势。

英文摘要:

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints. Full-model fine-tuning is computationally expensive and prone to overfitting, while parameter-efficient methods like LoRA apply adaptation uniformly across layers, overlooking internal representations thus compromising effectiveness and efficiency. We analyze multilingual ASR models and reveal a U-shaped adaptability pattern: early and late layers are language-specific and require more adaptation, while intermediate layers retain shared semantics and need less. Building on this observation, we propose DAMA, a Depth-Aware Model Adaptation framework that allocates adaptation capacity according to each layer's role. DAMA also introduces Singular Value Decomposition (SVD)-based initialization to constrain adaptation and preserve the U-shaped pattern, as well as a frozen middle-layer basis for further efficiency. Evaluated on 18 low-resource languages across two benchmark datasets, DAMA matches or surpasses state-of-the-art accuracy with 80% fewer trainable parameters, achieves a 29% error reduction under extreme data scarcity, and significantly improves memory, training time, and computational efficiency over baselines. These results highlight the benefits of structure-aware adaptation for efficient, scalable multilingual ASR.

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。

↑