Abstract
Code-switching (CS), a seamless alternation between languages within a single utterance, remains a critical challenge in automatic speech recognition (ASR). While prior works focus on conversational CS-ASR, enterprise settings demand evaluation of operational impact beyond edit-distance errors: how code-switching transcription errors propagate to downstream voice agent task failures. In this work, we propose (1) a CS-ASR synthetic benchmark and multidimensional evaluation framework tailored to enterprise domains, (2) systematic evaluation of frontier ASR systems across 5 language pairs, (3) diagnostic analysis of the additional transcription errors that code-switching introduces across language pairs and models. We release COSE-E to support enterprise-focused CSASR evaluation for multilingual voice agents in enterprise deployment.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Gupta, S., Nguyen, H. H., Huang, C., Brin, L. D., & Riols, F. (2026). CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings. https://omanscience.com/en/articles/cose-e-a-benchmark-for-code-switched-speech-evaluation-in-enterprise-settings
MLA 9
Gupta, Shama, et al. "CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings." https://omanscience.com/en/articles/cose-e-a-benchmark-for-code-switched-speech-evaluation-in-enterprise-settings.
Chicago (author–date)
Gupta, Shama, Hoang H Nguyen, Chelsea Huang, Lindsay Devon Brin, and Fanny Riols. 2026. "CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings." https://omanscience.com/en/articles/cose-e-a-benchmark-for-code-switched-speech-evaluation-in-enterprise-settings.
Harvard
Gupta, S., Nguyen, H. H., Huang, C., Brin, L. D. and Riols, F. (2026) 'CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings', Available at: https://omanscience.com/en/articles/cose-e-a-benchmark-for-code-switched-speech-evaluation-in-enterprise-settings.
Vancouver
Gupta S, Nguyen HH, Huang C, Brin LD, Riols F. CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings. https://omanscience.com/en/articles/cose-e-a-benchmark-for-code-switched-speech-evaluation-in-enterprise-settings
IEEE
S. Gupta, H. H. Nguyen, C. Huang, L. D. Brin, and F. Riols, "CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings," https://omanscience.com/en/articles/cose-e-a-benchmark-for-code-switched-speech-evaluation-in-enterprise-settings.