Metraipolis › archive › dc_bee8fb7e1214
HearInContext: A Benchmark for Implicit Context in Speech Recognition — arXiv:2609.18680
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18680
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T13:49:33.282Z
- SHA-256 of the archived text
e2ab01f27fa3f6f96b681c1eb3fba42891b77384ec7317812761d0cbd5769069- Stable URL of this page
https://metraipolis.com/documento/dc_bee8fb7e1214
How to cite
HearInContext: A Benchmark for Implicit Context in Speech Recognition — arXiv:2609.18680 — arXiv (en), https://arxiv.org/abs/2609.18680 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bee8fb7e1214 (Metraipolis archive dc_bee8fb7e1214, sha256 e2ab01f27fa3f6f96b681c1eb3fba42891b77384ec7317812761d0cbd5769069)
BibTeX
@misc{dcbee8fb7e1214,
title = {HearInContext: A Benchmark for Implicit Context in Speech Recognition — arXiv:2609.18680},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18680},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bee8fb7e1214; sha256 e2ab01f27fa3f6f96b681c1eb3fba42891b77384ec7317812761d0cbd5769069},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18680. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin-English benchmark that pairs shared synthetic speech with assistant replies supporting different interpretations. The benchmark comprises 3,764 semantic test cases built around homophones. Implicit contexts exclude candidate words; explicit contexts name the target. No-context and unrelated-context controls measure the benefit of relevant history and sensitivity to irrelevant history. Context-capable models benefit from implicit cues but achieve higher target recall with explicit hints. Fine-tuning Qwen3-ASR-1.7B improves implicit-context target recall by 11.4 percentage points in both Mandarin and English, while absolute CER/WER changes on AISHELL-1 and LibriSpeech remain below 0.1 percentage points. Gains extend to explicit conditions excluded from fine-tuning and to Mandarin hotword recognition on real recordings. Code and data are available at this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2609.18680 — 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 2026-10-15T13:48:24.337Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).