Several virtual and augmented reality tasks involve users in hands-free interactions; in this case, speech-based systems are often preferred for their intuitiveness and naturalness. On the other hand, the robustness of this kind of interfaces can be an issue, thus affecting both the usability and the user experience, when they are used in noisy environments. This paper proposes a one switch interface triggered by vocal commands: three different scanning algorithms are tested. With this kind of interface users can sequentially select the desired command, thus improving the robustness of traditional speech recognition-based interfaces. Latency time is an issue for one switch interfaces, but it is shown how a bidirectional scanning algorithm based on a non binary switch can strongly mitigate this problem. Vocal one switch (VOS) interfaces are compared with a traditional multi-word speech interface both objectively (in terms of robustness and efficiency) and subjectively (user feedback).
Vocal One Switch (VOS) selection interfaces for Virtual and Augmented Reality hands-free tasks / Manuri, Federico; Sanna, Andrea; Lamberti, Fabrizio; Paravati, Gianluca. - STAMPA. - (2016), pp. 79-87. (Intervento presentato al convegno Proc. Smart Tools and Apps in computer Graphics (STAG2016) tenutosi a Genova, Italy nel October 3-4, 2016) [10.2312/stag.20161367].
Vocal One Switch (VOS) selection interfaces for Virtual and Augmented Reality hands-free tasks
MANURI, FEDERICO;SANNA, Andrea;LAMBERTI, FABRIZIO;PARAVATI, GIANLUCA
2016
Abstract
Several virtual and augmented reality tasks involve users in hands-free interactions; in this case, speech-based systems are often preferred for their intuitiveness and naturalness. On the other hand, the robustness of this kind of interfaces can be an issue, thus affecting both the usability and the user experience, when they are used in noisy environments. This paper proposes a one switch interface triggered by vocal commands: three different scanning algorithms are tested. With this kind of interface users can sequentially select the desired command, thus improving the robustness of traditional speech recognition-based interfaces. Latency time is an issue for one switch interfaces, but it is shown how a bidirectional scanning algorithm based on a non binary switch can strongly mitigate this problem. Vocal one switch (VOS) interfaces are compared with a traditional multi-word speech interface both objectively (in terms of robustness and efficiency) and subjectively (user feedback).File | Dimensione | Formato | |
---|---|---|---|
paper-stag2016.pdf
accesso aperto
Descrizione: Articolo principale
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
445.56 kB
Formato
Adobe PDF
|
445.56 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2649146