|
1
|
Apicella A, Arpaia P, Giugliano S, Mastrati G, Moccaldi N. High-wearable EEG-based transducer for engagement detection in pediatric rehabilitation. BRAIN-COMPUTER INTERFACES 2021. [DOI: 10.1080/2326263x.2021.2015149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- Andrea Apicella
- Laboratory of Augmented Reality for Health Monitoring (Arhemlab), Department of Electrical Engineering and Information Technology, University of Naples Federico Ii, Naples, Italy
| | - Pasquale Arpaia
- Laboratory of Augmented Reality for Health Monitoring (Arhemlab), Department of Electrical Engineering and Information Technology, University of Naples Federico Ii, Naples, Italy
| | - Salvatore Giugliano
- Laboratory of Augmented Reality for Health Monitoring (Arhemlab), Department of Electrical Engineering and Information Technology, University of Naples Federico Ii, Naples, Italy
| | - Giovanna Mastrati
- Laboratory of Augmented Reality for Health Monitoring (Arhemlab), Department of Electrical Engineering and Information Technology, University of Naples Federico Ii, Naples, Italy
| | - Nicola Moccaldi
- Laboratory of Augmented Reality for Health Monitoring (Arhemlab), Department of Electrical Engineering and Information Technology, University of Naples Federico Ii, Naples, Italy
| |
Collapse
|
|
2
|
Andriella A, Torras C, Alenyà G. Cognitive System Framework for Brain-Training Exercise Based on Human-Robot Interaction. Cognit Comput 2020. [DOI: 10.1007/s12559-019-09696-2] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
|
3
|
|
|
4
|
Mišković D, Gnjatović M, Štrbac P, Trenkić B, Jakovljević N, Delić V. Hybrid methodological approach to context-dependent speech recognition. INT J ADV ROBOT SYST 2017. [DOI: 10.1177/1729881416687131] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022] Open
Abstract
Although the importance of contextual information in speech recognition has been acknowledged for a long time now, it has remained clearly underutilized even in state-of-the-art speech recognition systems. This article introduces a novel, methodologically hybrid approach to the research question of context-dependent speech recognition in human–machine interaction. To the extent that it is hybrid, the approach integrates aspects of both statistical and representational paradigms. We extend the standard statistical pattern-matching approach with a cognitively inspired and analytically tractable model with explanatory power. This methodological extension allows for accounting for contextual information which is otherwise unavailable in speech recognition systems, and using it to improve post-processing of recognition hypotheses. The article introduces an algorithm for evaluation of recognition hypotheses, illustrates it for concrete interaction domains, and discusses its implementation within two prototype conversational agents.
Collapse
Affiliation(s)
- Dragiša Mišković
- University of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia
| | - Milan Gnjatović
- University of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia
- School of Electrical and Computer Engineering of Applied Studies, Belgrade, Serbia
| | - Perica Štrbac
- School of Electrical and Computer Engineering of Applied Studies, Belgrade, Serbia
| | - Branimir Trenkić
- School of Electrical and Computer Engineering of Applied Studies, Belgrade, Serbia
| | - Nikša Jakovljević
- University of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia
| | - Vlado Delić
- University of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia
| |
Collapse
|
|
5
|
|
|
6
|
|
|
7
|
|