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

arXiv: https://arxiv.org/abs/2602.01008 · HTML: https://mlsanity.com/paper/2602.01008/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters](https://mlsanity.com/paper/2405.17604/) (2024)
- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks](https://mlsanity.com/paper/2405.15179/) (2024)
- [LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR](https://mlsanity.com/paper/2406.06619/) (2024)
- [Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages](https://mlsanity.com/paper/2511.09690/) (2025)
- [ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets](https://mlsanity.com/paper/2406.08641/) (2024)
- [Towards Lifelong Learning of End-to-end ASR](https://mlsanity.com/paper/2104.01616/) (2021)
- [CL-MASR: A Continual Learning Benchmark for Multilingual ASR](https://mlsanity.com/paper/2310.16931/) (2023)
- [Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting](https://mlsanity.com/paper/2203.16361/) (2022)
- [Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems](https://mlsanity.com/paper/2407.03645/) (2024)
- [CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning](https://mlsanity.com/paper/2507.04048/) (2025)
- [Efficient Multilingual ASR Finetuning via LoRA Language Experts](https://mlsanity.com/paper/2506.21555/) (2025)
- [Dark Experience for Incremental Keyword Spotting](https://mlsanity.com/paper/2409.08153/) (2024)
- [AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting](https://mlsanity.com/paper/2505.11817/) (2025)
- [Listen, Analyze, and Adapt to Learn New Attacks: An Exemplar-Free Class Incremental Learning Method for Audio Deepfake Source Tracing](https://mlsanity.com/paper/2505.14601/) (2025)
- [Language-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR](https://mlsanity.com/paper/2506.21577/) (2025)

## Built on by (most cited first, 1 of 1)

- [Continual Adaptation for Pacific Indigenous Speech Recognition](https://mlsanity.com/paper/2603.06310/) (2026)

## Abstract (arXiv)

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.