Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants

Andreea Danielescu; Sharone A. Horowit-Hendler; Alexandria Pabst; Kenneth Michael Stewart; Eric M. Gallo; Matthew Peter Aylett

doi:10.1145/3544548.3581281

Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants

Andreea Danielescu, Sharone A. Horowit-Hendler, Alexandria Pabst, Kenneth Michael Stewart, Eric M. Gallo, Matthew Peter Aylett

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

26 Citations (Scopus)

Abstract

As voice assistant usage continues to grow, their homogeneity becomes even more problematic with the UNESCO report, "I'd Blush if I could"showing that designing only feminine voice assistants encourages negative behavior, both with virtual assistants and with real people [3]. While masculine text-to-speech (TTS) voices exist, ones that cover the full range of gender presentations, such as non-binary or gender-ambiguous voices are largely missing. In this paper, we present a method of creating a non-binary TTS voice and an example voice, Sam, created with input from the non-binary and transgender communities. We have open-sourced the resulting voice, along with the process and data used to create it. Finally, we present results from a large-scale survey showing that non-binary individuals are more likely to prefer a non-binary voice assistant compared to cisgendered individuals and discuss differences across age and gender.

Original language	English
Title of host publication	CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450394215
DOIs	https://doi.org/10.1145/3544548.3581281
Publication status	Published - 19 Apr 2023
Event	2023 CHI Conference on Human Factors in Computing Systems: Socially Assistive Robots as Decision Makers: Transparency, Motivations, and Intentions - Hamburg, Germany Duration: 23 Apr 2023 → 28 Apr 2023

Conference

Conference	2023 CHI Conference on Human Factors in Computing Systems
Abbreviated title	CHI 2023
Country/Territory	Germany
City	Hamburg
Period	23/04/23 → 28/04/23

Keywords

gender
text-to-speech
voice assistants
voice user interfaces

ASJC Scopus subject areas

Human-Computer Interaction
Computer Graphics and Computer-Aided Design
Software

Access to Document

10.1145/3544548.3581281

Cite this

Danielescu, A., Horowit-Hendler, S. A., Pabst, A., Stewart, K. M., Gallo, E. M., & Aylett, M. P. (2023). Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants. In CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems Article 390 Association for Computing Machinery. https://doi.org/10.1145/3544548.3581281

@inproceedings{72a4e63012c144dea52407a5bf514746,

title = "Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants",

abstract = "As voice assistant usage continues to grow, their homogeneity becomes even more problematic with the UNESCO report, {"}I'd Blush if I could{"}showing that designing only feminine voice assistants encourages negative behavior, both with virtual assistants and with real people [3]. While masculine text-to-speech (TTS) voices exist, ones that cover the full range of gender presentations, such as non-binary or gender-ambiguous voices are largely missing. In this paper, we present a method of creating a non-binary TTS voice and an example voice, Sam, created with input from the non-binary and transgender communities. We have open-sourced the resulting voice, along with the process and data used to create it. Finally, we present results from a large-scale survey showing that non-binary individuals are more likely to prefer a non-binary voice assistant compared to cisgendered individuals and discuss differences across age and gender.",

keywords = "gender, text-to-speech, voice assistants, voice user interfaces",

author = "Andreea Danielescu and Horowit-Hendler, \{Sharone A.\} and Alexandria Pabst and Stewart, \{Kenneth Michael\} and Gallo, \{Eric M.\} and Aylett, \{Matthew Peter\}",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 2023 CHI Conference on Human Factors in Computing Systems : Socially Assistive Robots as Decision Makers: Transparency, Motivations, and Intentions, CHI 2023 ; Conference date: 23-04-2023 Through 28-04-2023",

year = "2023",

month = apr,

day = "19",

doi = "10.1145/3544548.3581281",

language = "English",

booktitle = "CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems",

publisher = "Association for Computing Machinery",

address = "United States",

}

Danielescu, A, Horowit-Hendler, SA, Pabst, A, Stewart, KM, Gallo, EM & Aylett, MP 2023, Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants. in CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems., 390, Association for Computing Machinery, 2023 CHI Conference on Human Factors in Computing Systems, Hamburg, Hamburg, Germany, 23/04/23. https://doi.org/10.1145/3544548.3581281

Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants. / Danielescu, Andreea; Horowit-Hendler, Sharone A.; Pabst, Alexandria et al.
CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2023. 390.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Creating Inclusive Voices for the 21st Century

T2 - 2023 CHI Conference on Human Factors in Computing Systems

AU - Danielescu, Andreea

AU - Horowit-Hendler, Sharone A.

AU - Pabst, Alexandria

AU - Stewart, Kenneth Michael

AU - Gallo, Eric M.

AU - Aylett, Matthew Peter

PY - 2023/4/19

Y1 - 2023/4/19

N2 - As voice assistant usage continues to grow, their homogeneity becomes even more problematic with the UNESCO report, "I'd Blush if I could"showing that designing only feminine voice assistants encourages negative behavior, both with virtual assistants and with real people [3]. While masculine text-to-speech (TTS) voices exist, ones that cover the full range of gender presentations, such as non-binary or gender-ambiguous voices are largely missing. In this paper, we present a method of creating a non-binary TTS voice and an example voice, Sam, created with input from the non-binary and transgender communities. We have open-sourced the resulting voice, along with the process and data used to create it. Finally, we present results from a large-scale survey showing that non-binary individuals are more likely to prefer a non-binary voice assistant compared to cisgendered individuals and discuss differences across age and gender.

AB - As voice assistant usage continues to grow, their homogeneity becomes even more problematic with the UNESCO report, "I'd Blush if I could"showing that designing only feminine voice assistants encourages negative behavior, both with virtual assistants and with real people [3]. While masculine text-to-speech (TTS) voices exist, ones that cover the full range of gender presentations, such as non-binary or gender-ambiguous voices are largely missing. In this paper, we present a method of creating a non-binary TTS voice and an example voice, Sam, created with input from the non-binary and transgender communities. We have open-sourced the resulting voice, along with the process and data used to create it. Finally, we present results from a large-scale survey showing that non-binary individuals are more likely to prefer a non-binary voice assistant compared to cisgendered individuals and discuss differences across age and gender.

KW - gender

KW - text-to-speech

KW - voice assistants

KW - voice user interfaces

UR - https://www.scopus.com/pages/publications/85160016399

U2 - 10.1145/3544548.3581281

DO - 10.1145/3544548.3581281

M3 - Conference contribution

AN - SCOPUS:85160016399

BT - CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

Y2 - 23 April 2023 through 28 April 2023

ER -

Creating Inclusive Voices for the 21st Century: A Non-Binary Text-to-Speech for Conversational Assistants

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this