Modelling Interest in Face-to-Face Conversations from Multimodal Nonverbal Behaviour

Gática-Pérez, Daniel

doi:10.1016/b978-0-12-374825-6.00020-4

Cited by 6 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gatica-Perez relates displayed level of engagement to interest, which he defines as a term used "to designate people's internal states related to the degree of engagement displayed, consciously or not, during social interaction." [3]. Non-verbal behaviours such as facial expression, gesture, and posture play a major role for humans when inferring information from partners [4], and such non-verbal cues have been proposed as perceptible factors that can be used to estimate engagement level [5].…”

Section: Engagementmentioning

confidence: 99%

Conversational Engagement Recognition Using Auditory and Visual Cues

2016

View full text Add to dashboard Cite

Automatic prediction of engagement in human-human and human-machine dyadic and multiparty interaction scenarios could greatly aid in evaluation of the success of communication. A corpus of eight face-to-face dyadic casual conversations was recorded and used as the basis for an engagement study, which examined the effectiveness of several methods of engagement level recognition. A convolutional neural network based analysis was seen to be the most effective.

show abstract

Section: Engagementmentioning

confidence: 99%

Conversational Engagement Recognition Using Auditory and Visual Cues

2016

View full text Add to dashboard Cite

show abstract

“…Based on studies [2][3][4][5][6][7][8][9] our hypotheses are: the higher the degree of involvement, (1) the higher the level and (2) the wider the span of the voice, (3) the quicker the articulation rate, (4) the higher the intensity and (5) the higher the amount of movement in the face and body of the participants.…”

Section: Main Objectives and Hypothesesmentioning

confidence: 99%

“…Studies on involvement [2], [4], or related concepts such as emotional engagement [5] [6], interest [7], or interactional rapport [8] reported that these phenomena are conveyed by specific prosodic cues. For example, Wrede and Shriberg [2], in their study on involvement found that there was an increase in mean and range of the fundamental frequency (F0) in more activated speech as well as tense voice quality.…”

Section: Introductionmentioning

confidence: 99%

Towards the Automatic Detection of Involvement in Conversation

Oertel

Looze

Scherer

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Although an increasing amount of research has been carried out into human-machine interaction in the last century, even today we are not able to fully understand the dynamic changes in human interaction. Only when we achieve this, will we be able to go beyond a one-to-one mapping between text and speech and be able to add social information to speech technologies. Social information is expressed to a high degree through prosodic cues and movement of the body and the face. The aim of this paper is to use those cues to make one aspect of social information more tangible; namely participants' degree of involvement in a conversation. Our results for voice span and intensity, and our preliminary results on the movement of the body and face suggest that these cues are reliable cues for the detection of distinct levels of participants involvement in conversation. This will allow for the development of a statistical model which is able to classify these stages of involvement. Our data indicate that involvement may be a scalar phenomenon.

show abstract

“…The ability of characters to express interest [GP09] in users through gaze [PPB*05] and associated modalities has led to research on less explicit and more natural ways in which interaction with humans is requested and human attention is directed. The ability to express interest through eye movements and gaze has been studied in relation to its effects on human perception of attention [Pet06] and human self‐involvement during social interactions [MSH*06] with characters.…”

Section: High‐level Aspects Of Gaze Behaviourmentioning

confidence: 99%