Metraipolis › archive › dc_8fe322d0fa9b
SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets — arXiv:2610.19869
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19869
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:39:04.154Z
- SHA-256 of the archived text
729b75802628961c4dd5039047cad593ecaca07f289dcf5b7baa736fd0e13032- Stable URL of this page
https://metraipolis.com/documento/dc_8fe322d0fa9b
How to cite
SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets — arXiv:2610.19869 — arXiv (en), https://arxiv.org/abs/2610.19869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8fe322d0fa9b (Metraipolis archive dc_8fe322d0fa9b, sha256 729b75802628961c4dd5039047cad593ecaca07f289dcf5b7baa736fd0e13032)
BibTeX
@misc{dc8fe322d0fa9b,
title = {SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets — arXiv:2610.19869},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19869},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8fe322d0fa9b; sha256 729b75802628961c4dd5039047cad593ecaca07f289dcf5b7baa736fd0e13032},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce SEA-HELM Audio, a Southeast Asian (SEA) multilingual evaluation framework that extends the text-based SEA-HELM benchmark to assess performance degradation in cascaded automatic speech recognition and large language model (ASR-LLM) pipelines. Using synthesized speech, we compare speech-input and text-input performance across five languages (Chinese, English, Malay, Indonesian, and Tamil) on multiple-choice reasoning and instruction-following tasks. We evaluate open-weight and commercial ASR-LLM systems using identical verifiers and quantify the speech gap as the difference between text and speech accuracy. Results show substantial degradation, with accuracy drops of 9.00 to 18.50 percentage points for multiple-choice reasoning and 20.00 to 42.86 points for instruction following. Tamil exhibits the largest degradation, exceeding 40 percentage points. Our findings highlight the limitations of text-only benchmarks in predicting voice-agent reliability and demonstrate the value of SEA-HELM Audio for evaluating multilingual voice-agent systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.19869 — 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 2026-10-15T19:36:18.298Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).