Metraipolis › archive › dc_ea62acf2befe

CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings — arXiv:2609.35645

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35645
License (as archived): CC0-1.0
Archived: 2026-10-07T21:54:21.221Z
SHA-256 of the archived text: 231da589fdf974c5ca2d98035f6a3297372676326253904196ea0ec7bfa20138
Stable URL of this page: https://metraipolis.com/documento/dc_ea62acf2befe

How to cite

CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings — arXiv:2609.35645 — arXiv (en), https://arxiv.org/abs/2609.35645 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea62acf2befe (Metraipolis archive dc_ea62acf2befe, sha256 231da589fdf974c5ca2d98035f6a3297372676326253904196ea0ec7bfa20138)

BibTeX

@misc{dcea62acf2befe,
  title = {CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings — arXiv:2609.35645},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35645},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea62acf2befe; sha256 231da589fdf974c5ca2d98035f6a3297372676326253904196ea0ec7bfa20138},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35645. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.35645 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T21:27:08.852Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).