[multi’vocal]: reflections on engaging everyday people in the development of a collective non-binary synthesized voice

The growing field of Human-Computer Interaction (HCI) takes a step out from conventional screenbased interactions, creating new scenarios, in which voice synthesis and voice recognition become important elements. Such voices are commonly created through concatenative or parametric synthesis methods, which access large voice corpora, pre-recorded by a single professional voice actor. These designed voices arguably propagate representations of gender binary identities. In this paper we present our project, [multi’vocal], which aims to challenge the current gender binary representations in synthesized voices. More specifically we explore if it is possible to create a non-binary synthesized voice through engaging everyday people of diverse backgrounds in giving voice to a collective synthesized voice of all genders, ages and accents.

Metadaten
Author:	Stina Hasse Jørgensen, Alice Baird GND, Frederik Tollund Juutilainen, Mads Pelt, Nina Cecilie Højholdt
URN:	urn:nbn:de:bvb:384-opus4-658892
Frontdoor URL	https://opus.bibliothek.uni-augsburg.de/opus4/65889
Parent Title (English):	Proceedings of EVA Copenhagen 2018, Aalborg University, Copenhagen, Denmark, 15 - 17 May 2018
Publisher:	BCS Learning & Development
Type:	Conference Proceeding
Language:	English
Year of first Publication:	2018
Publishing Institution:	Universität Augsburg
Release Date:	2019/11/22
DOI:	https://doi.org/10.14236/ewic/evac18.41
Institutes:	Fakultät für Angewandte Informatik
	Fakultät für Angewandte Informatik / Institut für Informatik
	Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Embedded Intelligence for Health Care and Wellbeing
Dewey Decimal Classification:	0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):	CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand)

Open Access