Metraipolis › archive › dc_85c6b2ec6ca1
VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis — arXiv:2609.03203
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03203
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:41:07.364Z
- SHA-256 of the archived text
a2061c4daf9478dd90760f10467d7d8b750b60f9368ce1a840362f303aef26d3- Stable URL of this page
https://metraipolis.com/documento/dc_85c6b2ec6ca1
How to cite
VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis — arXiv:2609.03203 — arXiv (en), https://arxiv.org/abs/2609.03203 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85c6b2ec6ca1 (Metraipolis archive dc_85c6b2ec6ca1, sha256 a2061c4daf9478dd90760f10467d7d8b750b60f9368ce1a840362f303aef26d3)
BibTeX
@misc{dc85c6b2ec6ca1,
title = {VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis — arXiv:2609.03203},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03203},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85c6b2ec6ca1; sha256 a2061c4daf9478dd90760f10467d7d8b750b60f9368ce1a840362f303aef26d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03203. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Plan accuracy alone cannot show whether a speech-delivery decision follows its source: a fixed prior may match the original label yet fail to respond appropriately when a cue changes. VoxReason provides a 100-case verifier benchmark that holds each utterance fixed, edits one designated source-label cue, and scores cited evidence, eight plan fields, and the permitted response. On a source-key-disjoint test of 24 cases, a source-emotion prior reaches plan-slot accuracy 0.958, but none of the 24 edited neutral targets appears in its training labels; its required-change accuracy is 0.000. This diagnoses the support boundary of this prior, not its performance on supported edits. In a complementary 32-case emotion-disjoint test, the prior has seen all edited neutral targets but neither original test emotion; its plan-slot accuracy is 0.219 and required-change accuracy is 1.000. The partitions reuse and overlap the same 100 cases, so these deterministic diagnostics are not independent cohorts or learned-planner results. The benchmark evaluates derived labels and structured plans, not audio input, generated speech, or listener judgments. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 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/2609.03203 — 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 2026-10-17T01:11:43.587Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).