Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs
Summary
This paper investigates whether code-switching ASR capabilities learned from limited seen language pairs can generalize to unseen pairs using model merging and domain generalization methods, finding only modest transfer.
View Cached Full Text
Cached at: 06/05/26, 06:06 AM
Paper page - Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs
Source: https://huggingface.co/papers/2606.05846
Abstract
Code-switching automatic speech recognition models show limited generalization across unseen language pairs despite attempts at model merging and domain generalization techniques.
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 throughsynthetic CS speech generationorpair-specific fine-tuningon 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 throughmodel merginganddomain generalizationmethods. 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.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2606\.05846
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.05846 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.05846 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.05846 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
Reinforcement Learning for Data-Efficient Code-Switched ASR
Introduces a reinforcement learning with verifiable rewards recipe for data-efficient adaptation of audio-language models to code-switched ASR, achieving significant gains across 10 language pairs with minimal data.
Real-time multilingual ASR using rolling buffers and monolingual models [P]
A routing-based approach for real-time multilingual ASR that uses smaller monolingual models with a rollback mechanism to handle language switches, achieving ~13% WER on inter-utterance code-switching and open-sourcing the system.
Efficient Multilingual Reasoning Transfer via Progressive Code-Switching
This paper introduces Progressive Code-Switching (PCS), a reinforcement learning approach with curriculum learning that gradually increases code-switching in LLMs to efficiently transfer multilingual reasoning capabilities.
Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
Proposes a POI-aware contrastive training framework using LLM-generated near-misses to improve ASR robustness at code-switching regions, achieving consistent error reductions on two benchmarks.
An In-Vitro Study on Cross-Lingual Generalization in Language Models
This paper introduces an in-vitro framework with two procedurally generated languages to study cross-lingual generalization in language models, finding that tokenization's preservation of reusable substructure is more critical than lexical similarity or data balance for transferring capabilities across languages.