# Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs

arXiv: https://arxiv.org/abs/2606.05846 · HTML: https://mlsanity.com/paper/2606.05846/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Arcee's MergeKit: A Toolkit for Merging Large Language Models](https://mlsanity.com/paper/2403.13257/) (2024)
- [The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results](https://mlsanity.com/paper/2007.05916/) (2020)
- [Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging](https://mlsanity.com/paper/2505.05464/) (2025)
- [Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models](https://mlsanity.com/paper/2410.01335/) (2024)
- [Unlocking the Potential of Model Merging for Low-Resource Languages](https://mlsanity.com/paper/2407.03994/) (2024)
- [TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline](https://mlsanity.com/paper/2206.13135/) (2022)
- [Improving Low Resource Code-switched ASR using Augmented Code-switched TTS](https://mlsanity.com/paper/2010.05549/) (2020)
- [OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging](https://mlsanity.com/paper/2505.19892/) (2025)
- [CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset](https://mlsanity.com/paper/2509.14161/) (2025)
- [Code-Switching Text Generation and Injection in Mandarin-English ASR](https://mlsanity.com/paper/2303.10949/) (2023)
- [CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition](https://mlsanity.com/paper/2502.18913/) (2025)
- [Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM](https://mlsanity.com/paper/2409.15905/) (2024)
- [Gradient-Guided Annealing for Domain Generalization](https://mlsanity.com/paper/2502.20162/) (2025)
- [Adapting the adapters for code-switching in multilingual ASR](https://mlsanity.com/paper/2310.07423/) (2023)
- [HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition](https://mlsanity.com/paper/2509.24613/) (2025)
- [Robust fine-tuning of speech recognition models via model merging: application to disordered speech](https://mlsanity.com/paper/2505.20477/) (2025)
- [DOTA-ME-CS: Daily Oriented Text Audio-Mandarin English-Code Switching Dataset](https://mlsanity.com/paper/2501.12122/) (2025)
- [AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR](https://mlsanity.com/paper/2506.14190/) (2025)
- [UniCoM: A Universal Code-Switching Speech Generator](https://mlsanity.com/paper/2508.15244/) (2025)
- [Group-Aware Partial Model Merging for Children's Automatic Speech Recognition](https://mlsanity.com/paper/2511.23098/) (2025)
- [Layer-wise Swapping for Generalizable Multilingual Safety](https://mlsanity.com/paper/2601.22620/) (2026)

## Abstract (arXiv)

Automatic Speech Recognition (ASR) has become a key technology for human--AI interaction. However, code-switching ASR (CS-ASR) remains particularly challenging due to the severe scarcity of multilingual CS speech resources across diverse language pairs. Existing approaches primarily improve CS-ASR performance through synthetic CS speech generation or pair-specific fine-tuning on limited bilingual datasets. Nevertheless, these approaches face an inherent scalability limitation, as support for CS must be developed separately for language pairs whose number grows combinatorially with the number of supported languages. In this work, we investigate whether CS capabilities learned from a limited set of seen language pairs can generalize to unseen language pairs through model merging and domain generalization methods. Our experiments show that merged bilingual CS-ASR models modestly generalize to unseen language pairs, suggesting limited transfer of bilingual CS capabilities across language pairs.