Saved in:
Bibliographic Details
Main Authors: Liu, Hexin, Zhang, Haoyang, Zhang, Qiquan, Zhang, Xiangyu, Shi, Dongyuan, Chng, Eng Siong, Li, Haizhou
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.24310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908891981283328
author Liu, Hexin
Zhang, Haoyang
Zhang, Qiquan
Zhang, Xiangyu
Shi, Dongyuan
Chng, Eng Siong
Li, Haizhou
author_facet Liu, Hexin
Zhang, Haoyang
Zhang, Qiquan
Zhang, Xiangyu
Shi, Dongyuan
Chng, Eng Siong
Li, Haizhou
contents Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges. In this paper, we systematically analyze CS-ASR from both model-centric and data-centric perspectives. By comparing state-of-the-art algorithmic methods, including language-specific processing and auxiliary language-aware multi-task learning, we discuss their varying effectiveness across datasets with different linguistic characteristics. On the data side, we first investigate TTS as a data augmentation method. By varying the textual characteristics and speaker accents, we analyze the impact of language confusion and accent bias on CS-ASR. To further mitigate data scarcity and enhance textual diversity, we propose a prompting strategy by simplifying the equivalence constraint theory (SECT) to guide large language models (LLMs) in generating linguistically valid code-switching text. The proposed SECT outperforms existing methods in ASR performance and linguistic quality assessments, generating code-switching text that more closely resembles real-world code-switching text. When used to generate speech-text pairs via TTS, SECT proves effective in improving CS-ASR performance. Our analysis of both model- and data-centric methods underscores that effective CS-ASR requires strategies to be carefully aligned with the specific linguistic characteristics of the code-switching data.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24310
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
Liu, Hexin
Zhang, Haoyang
Zhang, Qiquan
Zhang, Xiangyu
Shi, Dongyuan
Chng, Eng Siong
Li, Haizhou
Audio and Speech Processing
Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges. In this paper, we systematically analyze CS-ASR from both model-centric and data-centric perspectives. By comparing state-of-the-art algorithmic methods, including language-specific processing and auxiliary language-aware multi-task learning, we discuss their varying effectiveness across datasets with different linguistic characteristics. On the data side, we first investigate TTS as a data augmentation method. By varying the textual characteristics and speaker accents, we analyze the impact of language confusion and accent bias on CS-ASR. To further mitigate data scarcity and enhance textual diversity, we propose a prompting strategy by simplifying the equivalence constraint theory (SECT) to guide large language models (LLMs) in generating linguistically valid code-switching text. The proposed SECT outperforms existing methods in ASR performance and linguistic quality assessments, generating code-switching text that more closely resembles real-world code-switching text. When used to generate speech-text pairs via TTS, SECT proves effective in improving CS-ASR performance. Our analysis of both model- and data-centric methods underscores that effective CS-ASR requires strategies to be carefully aligned with the specific linguistic characteristics of the code-switching data.
title Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.24310