Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages
Year: 2026
Type: conference-paper
Abstract: 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 stateof-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.
Authors: Yang Xiao, Eun-Jung Holden, Ting Dang
Institution: The University of Melbourne
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166871599