Speech Driven Gaze in a Face-to-Face Interaction

Date

2021-03-01

Author

Arslan Aydin, Ulku
Kalkan, Sinan
Acartürk, Cengiz

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

222
views

0
downloads

Gaze and language are major pillars in multimodal communication. Gaze is a non-verbal mechanism that conveys crucial social signals in face-to-face conversation. However, compared to language, gaze has been less studied as a communication modality. The purpose of the present study is 2-fold: (i) to investigate gaze direction (i.e., aversion and face gaze) and its relation to speech in a face-to-face interaction; and (ii) to propose a computational model for multimodal communication, which predicts gaze direction using high-level speech features. Twenty-eight pairs of participants participated in data collection. The experimental setting was a mock job interview. The eye movements were recorded for both participants. The speech data were annotated by ISO 24617-2 Standard for Dialogue Act Annotation, as well as manual tags based on previous social gaze studies. A comparative analysis was conducted by Convolutional Neural Network (CNN) models that employed specific architectures, namely, VGGNet and ResNet. The results showed that the frequency and the duration of gaze differ significantly depending on the role of participant. Moreover, the ResNet models achieve higher than 70% accuracy in predicting gaze direction.

URI

https://hdl.handle.net/11511/89847

Journal

FRONTIERS IN NEUROROBOTICS

DOI

https://doi.org/10.3389/fnbot.2021.598895

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Signals of understanding in multilingual communication : a cross-linguistic functional-pragmatic analysis of interjections Akkuş, Mehmet; Daloğlu, Ayşegül; Department of English Language Teaching (2013) The main objective of this study is to investigate and find out the contribution of interjections as indicators of understanding in an Azerbaijani-Turkish Lingua Receptiva (LaRa) communication within the framework of Functional Pragmatics. The data utilized in this study were collected by video recording four Turkish and two university Azerbaijani native speakers who had paired each other and played a world famous guessing game Taboo. The length of data obtained from these recordings is circa two hours. The...
Linguistic Reflections on Psychotherapy: Change in Usage of The First Person Pronoun in Information Structure Positions Demiray, Cigdem Kose; Gençöz, Tülin (2018-08-01) Aim of present study was to understand changes in speech of clients with regard to certain linguistic features from 5th to 15th session of psychotherapy. First person pronoun use in information structure positions were analyzed in speech of clients. Participants of this study were 11 psychotherapists (clinical psychology master and doctorate students) and 16 clients (applicants to AYNA Psychotherapy Unit). In present study word count results of clinets' speeches were analyzed by ANOVA method. According to r...
Vocal synchrony as a coregulation indicator of attachment bonds Harma, Mehmet; Sümer, Nebi; Hazan, Cynthia; Department of Psychology (2014) This dissertation aims to explore the concept of coregulation in adulthood based on the analyses of vocal cues in conversations. Moderators which potentially affect vocal coordination between romantic partners were also examined. Twenty-four heterosexual dating couples (Mage = 21.25; SD = 1.03) from Cornell University were recruited for the Study-1. Participants communicated with their romantic and stranger partner in a balanced order. Their conversations were recorded and vocal features were extracted. Gra...
Emotion analysis of Turkish texts by using machine learning methods Boynukalın, Zeynep; Karagöz, Pınar; Department of Computer Engineering (2012) Automatically analysing the emotion in texts is in increasing interest in today’s research fields. The aim is to develop a machine that can detect type of user’s emotion from his/her text. Emotion classification of English texts is studied by several researchers and promising results are achieved. In this thesis, an emotion classification study on Turkish texts is introduced. To the best of our knowledge, this is the first study on emotion analysis of Turkish texts. In English there exists some well-defined...
Perceived benefits of three-way observation on the focal areas of abjectives of the activities, error-correction techniques and group-work in study conducted in an upper-intermediate class at Bilkent University school of English Language Uçan, Bengü Yurtseven; Daloğlu, Ayşegül; Department of English Language Teaching (2004) This study aims to explore the perceived benefits of three-way observation on the focal areas of objectives of the activities, error-correction techniques, and group-work in an upper-intermediate class in Bilkent University School of English Language. The data was collected through five classroom observations, six post-observation reflection sheets, five focus-group interviews with the students, and five post-observation interviews with the observer. A total of 15 upper-intermediate level students, one teac...

Citation Formats

U. Arslan Aydin, S. Kalkan, and C. Acartürk, “Speech Driven Gaze in a Face-to-Face Interaction,” FRONTIERS IN NEUROROBOTICS, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/89847.