Metraipolis › archive › dc_d87f162cc635

CommSketch: How Speaking while Sketching Steers Human--AI Design Ideation — arXiv:2609.37813

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37813
License (as archived): CC0-1.0
Archived: 2026-10-07T17:27:40.957Z
SHA-256 of the archived text: c195bbe16223e4599cdb788bb6b218becca14a41732438c5e6a01fe88965bd14
Stable URL of this page: https://metraipolis.com/documento/dc_d87f162cc635

How to cite

CommSketch: How Speaking while Sketching Steers Human--AI Design Ideation — arXiv:2609.37813 — arXiv (en), https://arxiv.org/abs/2609.37813 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d87f162cc635 (Metraipolis archive dc_d87f162cc635, sha256 c195bbe16223e4599cdb788bb6b218becca14a41732438c5e6a01fe88965bd14)

BibTeX

@misc{dcd87f162cc635,
  title = {CommSketch: How Speaking while Sketching Steers Human--AI Design Ideation — arXiv:2609.37813},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37813},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d87f162cc635; sha256 c195bbe16223e4599cdb788bb6b218becca14a41732438c5e6a01fe88965bd14},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37813. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Designers often speak while sketching when explaining ideas, yet AI design tools often rely on sketches or prompts, overlooking context expressed as ideas develop. We developed a sketch-based AI design interface that jointly interprets sketches and concurrent speech. Through a between-subjects study ($N=24$), we examined how speaking while sketching steers human--AI design ideation compared with sketches alone. For creativity support, concurrent speech supported natural expression of design intent and efficient visualisation. For human--AI collaboration, speech helped establish a shared understanding of design intent, supported significantly higher perceived alignment ($p<.05$), and enabled participants to guide AI contributions as ideas co-evolved. We discuss how future human--AI design tools could support dynamic alignment, broader multimodal expression, and human--AI co-creativity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.37813 — 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 2026-10-07T16:58:50.339Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).