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

Hugging Face Daily Papers Papers

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.

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.
Original Article
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

An In-Vitro Study on Cross-Lingual Generalization in Language Models

arXiv cs.CL

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.