Consistent categorization of multimodal integration patterns during human–computer interaction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00310704" target="_blank" >RIV/68407700:21230/17:00310704 - isvavai.cz</a>

Výsledek na webu

<a href="http://link.springer.com/article/10.1007/s12193-017-0243-1" target="_blank" >http://link.springer.com/article/10.1007/s12193-017-0243-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s12193-017-0243-1" target="_blank" >10.1007/s12193-017-0243-1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Consistent categorization of multimodal integration patterns during human–computer interaction

Popis výsledku v původním jazyce

Multimodal interaction represents a more natural style of human-computer interaction permitting our developed communicative skills to interact with computer systems. It remains a challenging task to design reliable multimodal systems. Employing advanced methods providing optimal performance depends on precise modeling of integration patterns that allows adapting to preferences and differences of individual users. While basic foundation and empirical evidence around these differences has already been described and confirmed in previous research works, introduced measures and classifications seem oversimplified and insufficiently precise to design reliable and robust interaction models. In this paper, results of our study of multimodal integration patterns in systems combining speech and gesture input are presented. Important interaction differences of subjects and their specific multimodal integration patterns were confirmed and completed with our own findings. Based on the obtained results, a new integration pattern categorization is defined and analyzed. The introduced categorization provides more reliable and consistent results in comparison with classifications presented in related literature. Moreover, its generality means it is applicable on other input modality combinations.

Název v anglickém jazyce

Consistent categorization of multimodal integration patterns during human–computer interaction

Popis výsledku anglicky

Multimodal interaction represents a more natural style of human-computer interaction permitting our developed communicative skills to interact with computer systems. It remains a challenging task to design reliable multimodal systems. Employing advanced methods providing optimal performance depends on precise modeling of integration patterns that allows adapting to preferences and differences of individual users. While basic foundation and empirical evidence around these differences has already been described and confirmed in previous research works, introduced measures and classifications seem oversimplified and insufficiently precise to design reliable and robust interaction models. In this paper, results of our study of multimodal integration patterns in systems combining speech and gesture input are presented. Important interaction differences of subjects and their specific multimodal integration patterns were confirmed and completed with our own findings. Based on the obtained results, a new integration pattern categorization is defined and analyzed. The introduced categorization provides more reliable and consistent results in comparison with classifications presented in related literature. Moreover, its generality means it is applicable on other input modality combinations.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal on Multimodal User Interfaces

ISSN

1783-7677

e-ISSN

1783-8738

Svazek periodika

2017

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

15

Strana od-do

251-265

Kód UT WoS článku

000408247600002

EID výsledku v databázi Scopus

2-s2.0-85015867567