# Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR

arXiv: https://arxiv.org/abs/2609.15758 · HTML: https://mlsanity.com/paper/2609.15758/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [Anisotropy Is Inherent to Self-Attention in Transformers](https://mlsanity.com/paper/2401.12143/) (2024)
- [IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages](https://mlsanity.com/paper/2403.01926/) (2024)
- [LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR](https://mlsanity.com/paper/2406.06619/) (2024)
- [Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition](https://mlsanity.com/paper/2012.01687/) (2020)
- [Exploiting Adapters for Cross-lingual Low-resource Speech Recognition](https://mlsanity.com/paper/2105.11905/) (2021)
- [Zero-shot cross-lingual transfer language selection using linguistic similarity](https://mlsanity.com/paper/2301.13720/) (2023)
- [Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages](https://mlsanity.com/paper/2305.12606/) (2023)
- [Learn and Don't Forget: Adding a New Language to ASR Foundation Models](https://mlsanity.com/paper/2407.06800/) (2024)
- [Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity](https://mlsanity.com/paper/2111.01326/) (2021)
- [Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition](https://mlsanity.com/paper/2207.03390/) (2022)
- [Swivuriso: The South African Next Voices Multilingual Speech Dataset](https://mlsanity.com/paper/2512.02201/) (2025)
- [Can Embedding Similarity Predict Cross-Lingual Transfer? A Systematic Study on African Languages](https://mlsanity.com/paper/2601.03168/) (2026)
- [Beyond WER: Probing Whisper's Sub-token Decoder Across Diverse Language Resource Levels](https://mlsanity.com/paper/2509.25516/) (2025)

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

- [Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition](https://mlsanity.com/paper/2609.29800/) (2026)

## Abstract (arXiv)

Extending large-scale multilingual automatic speech recognition (ASR) models to low-resource languages remains challenging. Model performance is skewed toward high-resource languages and degrades sharply for languages with limited labeled data and pre-training exposure. To address this, we investigate parameter-efficient approaches for transferring knowledge from resource-rich source languages to low-resource target languages on Whisper. Alongside warm initialization and attention-based fusion, we propose Sequential Adapter Stacking, which places a trainable target-language adapter on top of a frozen source-language adapter. Under controlled experiments, these approaches are evaluated on three target languages unsupported by Whisper -- Asturian, Assamese, and Xhosa -- using source languages with varying degrees of relatedness. Sequential Adapter Stacking with the closest related source consistently and significantly outperforms full fine-tuning across the three targets, with 5--8% relative WER reductions. These gains largely persist with only one hour of target training data.