{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:06:31Z","timestamp":1784307991268,"version":"3.55.0"},"reference-count":89,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007569","name":"Carl Zeiss Foundation","doi-asserted-by":"publisher","award":["P2022-06-004"],"award-info":[{"award-number":["P2022-06-004"]}],"id":[{"id":"10.13039\/100007569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Forschung, Technologie und Raumfahrt","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Graphics"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cag.2026.104632","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T23:57:40Z","timestamp":1781827060000},"page":"104632","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["VocalVis: Bridging voice-based control and 3D surface visualization"],"prefix":"10.1016","volume":"138","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5035-8233","authenticated-orcid":false,"given":"Jan","family":"Hombeck","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henrik","family":"Voigt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasna","family":"Nuhic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monique","family":"Meuschke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Lawonn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cag.2026.104632_b1","article-title":"Towards natural language interfaces for data visualization: A survey","author":"Shen","year":"2022","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"3","key":"10.1016\/j.cag.2026.104632_b2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3484221","article-title":"It\u2019s good to talk: A comparison of using voice versus screen-based interactions for agent-assisted tasks","volume":"29","author":"Reicherts","year":"2022","journal-title":"ACM Trans Comput-Hum Interact"},{"issue":"12","key":"10.1016\/j.cag.2026.104632_b3","doi-asserted-by":"crossref","first-page":"2689","DOI":"10.1109\/TVCG.2012.204","article-title":"Beyond mouse and keyboard: Expanding design considerations for information visualization interactions","volume":"18","author":"Lee","year":"2012","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"1","key":"10.1016\/j.cag.2026.104632_b4","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/TVCG.2017.2744684","article-title":"Applying pragmatics principles for interaction with visual analytics","volume":"24","author":"Hoque","year":"2017","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"10.1016\/j.cag.2026.104632_b5","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/s00778-019-00588-3","article-title":"Making data visualization more efficient and effective: a survey","volume":"29","author":"Qin","year":"2020","journal-title":"VLDB J"},{"issue":"3","key":"10.1016\/j.cag.2026.104632_b6","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.visinf.2020.07.002","article-title":"A survey on automatic infographics and visualization recommendations","volume":"4","author":"Zhu","year":"2020","journal-title":"Vis Inform"},{"key":"10.1016\/j.cag.2026.104632_b7","series-title":"Proc. of IEEE symposium on information visualization","first-page":"111","article-title":"Low-level components of analytic activity in information visualization","author":"Amar","year":"2005"},{"key":"10.1016\/j.cag.2026.104632_b8","series-title":"Distance visualizations for vascular structures in desktop and VR: Overview and implementation","first-page":"1","author":"Hombeck","year":"2022"},{"key":"10.1016\/j.cag.2026.104632_b9","first-page":"1877","article-title":"Language models are few-shot learners","volume":"vol. 33","author":"Brown","year":"2020"},{"key":"10.1016\/j.cag.2026.104632_b10","series-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b11","series-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b12","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b13","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"vol. 36","author":"Rafailov","year":"2024"},{"key":"10.1016\/j.cag.2026.104632_b14","article-title":"Toolformer: Language models can teach themselves to use tools","volume":"vol. 36","author":"Schick","year":"2024"},{"key":"10.1016\/j.cag.2026.104632_b15","unstructured":"Srinivasan VK, Dong Z, Zhu B, Yu B, Mosk-Aoyama D, Keutzer K, et al. NexusRaven: A commercially-permissive Language Model for function calling. In: Proc. of neurIPS workshop. 2023."},{"key":"10.1016\/j.cag.2026.104632_b16","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","article-title":"VIST5: An adaptive, retrieval-augmented language model for visualization-oriented dialog","author":"Voigt","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b17","series-title":"Mistral 7B","author":"Jiang","year":"2023"},{"issue":"1","key":"10.1016\/j.cag.2026.104632_b18","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1109\/TVCG.2021.3114770","article-title":"Accessible visualization via natural language descriptions: A four-level model of semantic content","volume":"28","author":"Lundgard","year":"2021","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"7s","key":"10.1016\/j.cag.2026.104632_b19","first-page":"201","article-title":"Vize: A voice-based interface for data visualization and summarisation with recommendation system","volume":"12","author":"Vasoya","year":"2024","journal-title":"Int J Intell Syst Appl Eng"},{"key":"10.1016\/j.cag.2026.104632_b20","doi-asserted-by":"crossref","unstructured":"\u0151zcan F, Quamar A, Sen J, Lei C, Efthymiou V. State of the art and open challenges in natural language interfaces to data. In: Proc. of ACM SIGMOD int conf manag data. 2020, p. 2629\u201336.","DOI":"10.1145\/3318464.3383128"},{"key":"10.1016\/j.cag.2026.104632_b21","doi-asserted-by":"crossref","unstructured":"Mathew M, Bagal V, Tito R, Karatzas D, Valveny E, Jawahar C. Infographicvqa. In: Proc. of WACV. 2022, p. 1697\u2013706.","DOI":"10.1109\/WACV51458.2022.00264"},{"issue":"3","key":"10.1016\/j.cag.2026.104632_b22","doi-asserted-by":"crossref","first-page":"65","DOI":"10.3390\/info9030065","article-title":"Storytelling and visualization: An extended survey","volume":"9","author":"Tong","year":"2018","journal-title":"Information"},{"key":"10.1016\/j.cag.2026.104632_b23","doi-asserted-by":"crossref","unstructured":"Luo Y, Tang N, Li G, Chai C, Li W, Qin X. Synthesizing natural language to visualization (NL2VIS) benchmarks from NL2SQL benchmarks. In: Proceedings of the 2021 international conference on management of data. 2021, p. 1235\u201347.","DOI":"10.1145\/3448016.3457261"},{"issue":"1","key":"10.1016\/j.cag.2026.104632_b24","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1109\/TVCG.2016.2599030","article-title":"Vega-lite: A grammar of interactive graphics","volume":"23","author":"Satyanarayan","year":"2016","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"10.1016\/j.cag.2026.104632_b25","doi-asserted-by":"crossref","first-page":"45181","DOI":"10.1109\/ACCESS.2023.3274199","article-title":"Chat2vis: Generating data visualizations via natural language using chatgpt, codex and gpt-3 large language models","volume":"11","author":"Maddigan","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.cag.2026.104632_b26","series-title":"LIDA: A tool for automatic generation of grammar-agnostic visualizations and infographics using large language models","author":"Dibia","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b27","series-title":"Text2Vis: A challenging and diverse benchmark for generating multimodal visualizations from text","author":"Rahman","year":"2025"},{"key":"10.1016\/j.cag.2026.104632_b28","doi-asserted-by":"crossref","unstructured":"Gao T, Dontcheva M, Adar E, Liu Z, Karahalios KG. Datatone: Managing ambiguity in natural language interfaces for data visualization. In: Proc. of UIST. 2015, p. 489\u2013500.","DOI":"10.1145\/2807442.2807478"},{"issue":"2","key":"10.1016\/j.cag.2026.104632_b29","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TVCG.2020.3030378","article-title":"NL4DV: A toolkit for generating analytic specifications for data visualization from natural language queries","volume":"27","author":"Narechania","year":"2020","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"10.1016\/j.cag.2026.104632_b30","doi-asserted-by":"crossref","unstructured":"Setlur V, Battersby SE, Tory M, Gossweiler R, Chang AX. Eviza: A natural language interface for visual analysis. In: Proc. of UIST. 2016, p. 365\u201377.","DOI":"10.1145\/2984511.2984588"},{"key":"10.1016\/j.cag.2026.104632_b31","series-title":"Proc. of ICSC","first-page":"196","article-title":"Nicky: Toward a virtual assistant for test and measurement instrument recommendations","author":"Kincaid","year":"2017"},{"issue":"1","key":"10.1016\/j.cag.2026.104632_b32","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/TVCG.2017.2745219","article-title":"Orko: Facilitating multimodal interaction for visual exploration and analysis of networks","volume":"24","author":"Srinivasan","year":"2017","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"3","key":"10.1016\/j.cag.2026.104632_b33","first-page":"175","article-title":"Attention, intentions, and the structure of discourse","volume":"12","author":"Grosz","year":"1986","journal-title":"Comput Linguist"},{"key":"10.1016\/j.cag.2026.104632_b34","series-title":"Wav2Vec: Unsupervised pre-training for speech recognition","author":"Schneider","year":"2019"},{"key":"10.1016\/j.cag.2026.104632_b35","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.cag.2026.104632_b36","series-title":"Proc. of ICML","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b37","series-title":"S3C@ cHItaly","first-page":"1","article-title":"Automatic speech recognition (ASR) with Whisper: Testing Performances in Different Languages","author":"Amorese","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b38","doi-asserted-by":"crossref","unstructured":"Koenecke A, Choi ASG, Mei KX, Schellmann H, Sloane M. Careless whisper: Speech-to-text hallucination harms. In: Proceedings of the 2024 ACM conference on fairness, accountability, and transparency. 2024, p. 1672\u201381.","DOI":"10.1145\/3630106.3658996"},{"key":"10.1016\/j.cag.2026.104632_b39","doi-asserted-by":"crossref","unstructured":"Bondarenko Y, Nagel M, Blankevoort T. Understanding and Overcoming the Challenges of Efficient Transformer Quantization. In: Proc. of EMNLP. 2021.","DOI":"10.18653\/v1\/2021.emnlp-main.627"},{"key":"10.1016\/j.cag.2026.104632_b40","doi-asserted-by":"crossref","first-page":"30318","DOI":"10.52202\/068431-2198","article-title":"GPT3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.cag.2026.104632_b41","series-title":"Quantization for OpenAI\u2019s whisper models: A comparative analysis","author":"Andreyev","year":"2025"},{"issue":"2","key":"10.1016\/j.cag.2026.104632_b42","first-page":"33","article-title":"Revolution or evolution? Speech interaction and HCI design guidelines","volume":"18","author":"Murad","year":"2019","journal-title":"Pc"},{"key":"10.1016\/j.cag.2026.104632_b43","doi-asserted-by":"crossref","unstructured":"Murad C, Candello H, Munteanu C. What\u2019s The Talk on VUI Guidelines? A Meta-Analysis of Guidelines for Voice User Interface Design. In: Proc. of the CUI. 2023, p. 1\u201316.","DOI":"10.1145\/3571884.3597129"},{"issue":"12","key":"10.1016\/j.cag.2026.104632_b44","doi-asserted-by":"crossref","first-page":"2122","DOI":"10.1109\/TVCG.2014.2346452","article-title":"The effects of interactive latency on exploratory visual analysis","volume":"20","author":"Liu","year":"2014","journal-title":"IEEE Trans Vis Comput Graphics"},{"key":"10.1016\/j.cag.2026.104632_b45","series-title":"Response times: the three important limits","author":"Nielsen","year":"1993"},{"key":"10.1016\/j.cag.2026.104632_b46","first-page":"1","article-title":"The model human processor- An engineering model of human performance","volume":"vol. 2","author":"Card","year":"1986"},{"issue":"6","key":"10.1016\/j.cag.2026.104632_b47","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/TVCG.2007.70539","article-title":"Animated transitions in statistical data graphics","volume":"13","author":"Heer","year":"2007","journal-title":"IEEE Trans Vis Comput Graphics"},{"issue":"08","key":"10.1016\/j.cag.2026.104632_b48","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/MC.1983.1654471","article-title":"Direct manipulation: A step beyond programming languages","volume":"16","author":"Shneiderman","year":"1983","journal-title":"Computer"},{"issue":"6","key":"10.1016\/j.cag.2026.104632_b49","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/TVCG.2007.70515","article-title":"Toward a deeper understanding of the role of interaction in information visualization","volume":"13","author":"Yi","year":"2007","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"4","key":"10.1016\/j.cag.2026.104632_b50","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1109\/TVCG.2005.63","article-title":"Knowledge precepts for design and evaluation of information visualizations","volume":"11","author":"Amar","year":"2005","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"10.1016\/j.cag.2026.104632_b51","series-title":"Proc. of IEEE symposium on information visualization","first-page":"1","article-title":"An evaluation of microarray visualization tools for biological insight","author":"Saraiya","year":"2004"},{"issue":"3","key":"10.1016\/j.cag.2026.104632_b52","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1007\/s10772-023-10036-x","article-title":"Voice user interfaces in manufacturing logistics: A literature review","volume":"26","author":"Ludwig","year":"2023","journal-title":"Int J Speech Technol"},{"key":"10.1016\/j.cag.2026.104632_b53","series-title":"Advances in production management systems. artificial intelligence for sustainable and resilient production systems: IFIP WG 5.7 international conference, APMS 2021, nantes, France, September 5\u20139, 2021, proceedings, part IV","first-page":"321","article-title":"Anatomy of a digital assistant","author":"Wellsandt","year":"2021"},{"key":"10.1016\/j.cag.2026.104632_b54","first-page":"9921","article-title":"The role of voice input for human-machine communication","volume":"vol. 92","author":"Cohen","year":"1995"},{"key":"10.1016\/j.cag.2026.104632_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2024.104069","article-title":"Voice user interfaces for effortless navigation in medical virtual reality environments","author":"Hombeck","year":"2024","journal-title":"Comput Graph"},{"issue":"8","key":"10.1016\/j.cag.2026.104632_b56","doi-asserted-by":"crossref","first-page":"4718","DOI":"10.1080\/10447318.2024.2352932","article-title":"Improving error correction and text editing using voice and mouse multimodal interface","volume":"41","author":"Taieb-Maimon","year":"2025","journal-title":"Int J Human\u2013Comput Interact"},{"key":"10.1016\/j.cag.2026.104632_b57","doi-asserted-by":"crossref","unstructured":"Sengupta K, Bhattarai S, Sarcar S, MacKenzie IS, Staab S. Leveraging error correction in voice-based text entry by Talk-and-Gaze. In: Proceedings of the 2020 CHI conference on human factors in computing systems. 2020, p. 1\u201311.","DOI":"10.1145\/3313831.3376579"},{"key":"10.1016\/j.cag.2026.104632_b58","series-title":"2022 IEEE visualization and visual analytics","first-page":"6","article-title":"Facilitating conversational interaction in natural language interfaces for visualization","author":"Mitra","year":"2022"},{"key":"10.1016\/j.cag.2026.104632_b59","series-title":"Proc. of IEEE conference virtual reality and 3D user interfaces","first-page":"123","article-title":"Tell me where to go: Voice-controlled hands-free locomotion for virtual reality systems","author":"Hombeck","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2025.104318","article-title":"Beyond buttons: A user-centric approach to hands-free locomotion in Virtual Reality via voice commands","author":"Hombeck","year":"2025","journal-title":"Comput Graph"},{"issue":"2","key":"10.1016\/j.cag.2026.104632_b61","first-page":"536","article-title":"A voice-based annotation system for collaborative computer-aided design","volume":"8","author":"Plumed","year":"2021","journal-title":"J Comput Des Eng"},{"key":"10.1016\/j.cag.2026.104632_b62","series-title":"Proc. of HCI international","first-page":"347","article-title":"IVOrpheus 2.0-A proposal for interaction by voice command-control in three dimensional environments of information visualization","author":"Furtado","year":"2016"},{"key":"10.1016\/j.cag.2026.104632_b63","series-title":"Proc. of SIGRAD","first-page":"17Y22","article-title":"3D visualization and 3D and voice interaction in air traffic management","author":"Lange","year":"2003"},{"key":"10.1016\/j.cag.2026.104632_b64","series-title":"Proc. of ICAEEE","first-page":"1","article-title":"3D natural interaction for an augmented reality system","author":"Mouna","year":"2019"},{"key":"10.1016\/j.cag.2026.104632_b65","series-title":"Proc. of the craft of information visualization","first-page":"364","article-title":"The Eyes Have It: A task by data type taxonomy for information visualizations","author":"Shneiderman","year":"2003"},{"issue":"2","key":"10.1016\/j.cag.2026.104632_b66","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1145\/2133416.2146416","article-title":"Interactive dynamics for visual analysis: A taxonomy of tools that support the fluent and flexible use of visualizations","volume":"10","author":"Heer","year":"2012","journal-title":"Queue"},{"issue":"3","key":"10.1016\/j.cag.2026.104632_b67","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.jvlc.2011.02.003","article-title":"A conceptual framework and taxonomy of techniques for analyzing movement","volume":"22","author":"Andrienko","year":"2011","journal-title":"J Vis Lang Comput"},{"issue":"12","key":"10.1016\/j.cag.2026.104632_b68","doi-asserted-by":"crossref","first-page":"2376","DOI":"10.1109\/TVCG.2013.124","article-title":"A multi-level typology of abstract visualization tasks","volume":"19","author":"Brehmer","year":"2013","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"1","key":"10.1016\/j.cag.2026.104632_b69","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1109\/TVCG.2018.2865145","article-title":"Augmenting visualizations with interactive data facts to facilitate interpretation and communication","volume":"25","author":"Srinivasan","year":"2018","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"239","key":"10.1016\/j.cag.2026.104632_b70","first-page":"2","article-title":"Docker: lightweight linux containers for consistent development and deployment","volume":"2014","author":"Merkel","year":"2014","journal-title":"Linux J"},{"key":"10.1016\/j.cag.2026.104632_b71","series-title":"Faster-whisper: Faster Whisper transcription with CTranslate2","author":"Klein","year":"2025"},{"key":"10.1016\/j.cag.2026.104632_b72","series-title":"Toward interactive dictation","author":"Li","year":"2023"},{"key":"10.1016\/j.cag.2026.104632_b73","series-title":"Deepseek LLM: Scaling open-source language models with longtermism","author":"Bi","year":"2024"},{"key":"10.1016\/j.cag.2026.104632_b74","series-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"issue":"1","key":"10.1016\/j.cag.2026.104632_b75","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1109\/TVCG.2018.2864509","article-title":"Visual analysis of aneurysm data using statistical graphics","volume":"25","author":"Meuschke","year":"2018","journal-title":"IEEE Trans Vis Comput Graph"},{"key":"10.1016\/j.cag.2026.104632_b76","first-page":"717","article-title":"36-Paraview: An end-user tool for large-data visualization","volume":"717","author":"Ahrens","year":"2005","journal-title":"Vis Handb"},{"issue":"7","key":"10.1016\/j.cag.2026.104632_b77","first-page":"88","article-title":"Design and validation of a framework for the creation of user experience questionnaires","volume":"5","author":"Martin","year":"2019","journal-title":"Int J Interact Multimed Artif Intell"},{"key":"10.1016\/j.cag.2026.104632_b78","series-title":"Proc. of HCII","first-page":"167","article-title":"Design and evaluation of voice user interfaces: What should one consider?","author":"Klein","year":"2023"},{"issue":"8","key":"10.1016\/j.cag.2026.104632_b79","article-title":"Paraview: An end-user tool for large data visualization","volume":"717","author":"Ahrens","year":"2005","journal-title":"Vis Handb"},{"key":"10.1016\/j.cag.2026.104632_b80","series-title":"The paraview tutorial","author":"Moreland","year":"2013"},{"issue":"4","key":"10.1016\/j.cag.2026.104632_b81","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1006\/imms.1993.1078","article-title":"Speech versus mouse commands for word processing: an empirical evaluation","volume":"39","author":"Karl","year":"1993","journal-title":"Int J Man-Mach Stud"},{"key":"10.1016\/j.cag.2026.104632_b82","doi-asserted-by":"crossref","unstructured":"Oviatt S, Coulston R, Lunsford R. When do we interact multimodally? Cognitive load and multimodal communication patterns. In: Proceedings of the 6th international conference on multimodal interfaces. 2004, p. 129\u201336.","DOI":"10.1145\/1027933.1027957"},{"key":"10.1016\/j.cag.2026.104632_b83","doi-asserted-by":"crossref","unstructured":"Oviatt S, Coulston R, Tomko S, Xiao B, Lunsford R, Wesson M, Carmichael L. Toward a theory of organized multimodal integration patterns during human-computer interaction. In: Proceedings of the 5th international conference on multimodal interfaces. 2003, p. 44\u201351.","DOI":"10.1145\/958432.958443"},{"issue":"11","key":"10.1016\/j.cag.2026.104632_b84","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1145\/319382.319398","article-title":"Ten myths of multimodal interaction","volume":"42","author":"Oviatt","year":"1999","journal-title":"Comm ACM"},{"issue":"1\u20132","key":"10.1016\/j.cag.2026.104632_b85","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1207\/s15327051hci1201&2_4","article-title":"Mulitmodal interactive maps: Designing for human performance","volume":"12","author":"Oviatt","year":"1997","journal-title":"Human\u2013Comput Interact"},{"key":"10.1016\/j.cag.2026.104632_b86","doi-asserted-by":"crossref","unstructured":"Christian K, Kules B, Shneiderman B, Youssef A. A comparison of voice controlled and mouse controlled web browsing. In: Proceedings of the fourth international ACM conference on assistive technologies. 2000, p. 72\u20139.","DOI":"10.1145\/354324.354345"},{"key":"10.1016\/j.cag.2026.104632_b87","series-title":"User centered system design","first-page":"87","article-title":"Direct manipulation interfaces","author":"Hutchins","year":"1986"},{"key":"10.1016\/j.cag.2026.104632_b88","series-title":"2022 IEEE conference on virtual reality and 3D user interfaces","first-page":"514","article-title":"Evaluating perceptional tasks for medicine: A comparative user study between a virtual reality and a desktop application","author":"Hombeck","year":"2022"},{"issue":"6","key":"10.1016\/j.cag.2026.104632_b89","doi-asserted-by":"crossref","DOI":"10.2196\/14827","article-title":"Effect of speech recognition on problem solving and recall in consumer digital health tasks: controlled laboratory experiment","volume":"22","author":"Chen","year":"2020","journal-title":"J Med Internet Res"}],"container-title":["Computers & Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001032?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001032?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:31:14Z","timestamp":1784305874000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0097849326001032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":89,"alternative-id":["S0097849326001032"],"URL":"https:\/\/doi.org\/10.1016\/j.cag.2026.104632","relation":{},"ISSN":["0097-8493"],"issn-type":[{"value":"0097-8493","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VocalVis: Bridging voice-based control and 3D surface visualization","name":"articletitle","label":"Article Title"},{"value":"Computers & Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cag.2026.104632","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"104632"}}