research-article

Discrimination analysis of intelligent voice assistants

Authors:

Elizabeth Sucupira Furtado,

Virgilio Almeida,

Thiago H. O. da SilvaAuthors Info & Claims

IHC '19: Proceedings of the 18th Brazilian Symposium on Human Factors in Computing Systems

Article No.: 22, Pages 1 - 7

https://doi.org/10.1145/3357155.3358483

Published: 22 October 2019 Publication History

Abstract

Assistentes de Voz Inteligentes (AVI) estão se tornando cada vez mais populares em todo o mundo, provendo fácil interação para realização de serviços e acessos a dispositivos. No entanto, o treinamento desses assistentes de voz pode estar limitado a falas padronizadas gerando o risco de desestimular a adoção desta tecnologia inclusiva por grupos com características de fala distintas da padrão. A eventual diferença de qualidade de desempenho dos assistentes em virtude das formas específicas da fala de diferentes grupos de pessoas nos países em desenvolvimento pode ser considerado um viés, bem como um fator que discriminará principalmente os grupos mais vulneráveis e, consequentemente, aumentará a lacuna digital nestes países. Neste trabalho, apresentamos um estudo de caso que analisa a presença de viés na interação por voz com os assistentes, ou seja, uma diferença na qualidade do desempenho dadas características específicas de fala dos usuários. Avaliamos o comportamento do Google Assistente e da Siri para grupos de pessoas distribuídas por gênero e região do país, avaliando duas características da linguagem: a cacoépia e a disfluência. Resultados preliminares indicam que a cacoépia e a disfluência estão relacionadas com a região de origem do falante e têm impacto no desempenho dos assistentes de voz.

References

[1]

J Maxwell Atkinson and John Heritage. 1999. Transcript notation-Structures of social action: studies in conversation analysis. Aphasiology 13, 4--5 (1999), 243--249.

[2]

Ricardo Baeza-Yates. 2018. Bias on the web. Commun. ACM 61, 6 (2018), 54--61.

Digital Library

[3]

Marcos Bagno. 1999. Preconceito lingüístico: o que é, como sefaz. Edições Loyola.

[4]

Jerome R Bellegarda. 2014. Spoken language understanding for natural interaction: The siri experience. In Natural Interaction with Robots, Knowbots and Smartphones. Springer, 3--14.

[5]

Suzana Alice Cardoso. 2014. Atlas linguístico do Brasil. Vol. 1. SciELO-EDUEL.

[6]

Estado de São Paulo Newspaper. 2017. WhatsApp chega a 120 milhões de usuarios no Brasil.

[7]

NÚCLEO DE APOIO DE SANTO ANDRÉ. [n. d.]. VÍCIOS DE LINGUAGUEM PRESENTES NO DIA-A-DIA. ([n. d.]).

[8]

Adriana de Souza e Silva, Daniel M Sutko, Fernando A Salis, and Claudio de Souza e Silva. 2011. Mobile phone appropriation in the favelas of Rio de Janeiro, Brazil. New Media & Society 13, 3 (2011), 411--426.

[9]

Caroline Floccia, Jeremy Goslin, Frédérique Girard, and Gabrielle Konopczynski. 2006. Does a regional accent perturb speech processing? Journal of Experimental Psychology: Human Perception and Performance 32, 5 (2006), 1276.

[10]

Reuters Institute. 2018. The Future of Voice and the Implications for News.

[11]

Lanna Lima, Vasco Furtado, Elizabeth Furtado, and Virgilio Almeida. 2019. Empirical Analysis of Bias in Voice-based Personal Assistants. In Companion Proceedings of The 2019 World Wide Web Conference. ACM, 533--538.

[12]

Karen Livescu. 2008. Phonological models in automatic speech recognition: invited talk. In Proceedings of the Tenth Meeting of ACL Special Interest Group on Computational Morphology and Phonology. Association for Computational Linguistics, 1--1.

[13]

Ana Elis Nogueira de MAGALHÃES ANDRADE and Renira CIRELLI APPA. [n. d.]. Fonologia: Prosódia e ortoépia um estudo com base nas transcrições de conversações em telemarketing entre pessoas jurídicas (BankBoston). Revista Letra Magna 02 ([n. d.]).

[14]

Wired Magazine. 2017. Voice Is the Next Big Platform, Unless You Have an Accent.

[15]

Rami Matarneh, Svitlana Maksymova, Vyacheslav Lyashenko, and N Belova. 2017. Speech recognition systems: A comparative review. (2017).

[16]

Helena Moniz, Ana Isabel Mata, and Isabel Trancoso. 2011. A classificação das disfluências como mecanismos de (dis) fluência e os seus contextos prosódicos. Textos Seleccionados do XXVI Encontro Nacional da APL (2011).

[17]

Sharon Oviatt. 1994. Interface techniques for minimizing disfluent input to spoken language systems. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 205--210.

Digital Library

[18]

Tyler K Perrachione. 2017. Speaker recognition across languages. Oxford University Press.

[19]

Martin Porcheron, Joel E Fischer, Stuart Reeves, and Sarah Sharples. 2018. Voice interfaces in everyday life. In proceedings of the 2018 CHI conference on human factors in computing systems. ACM, 640.

Digital Library

[20]

W Nicholson Price. 2018. Big data and black-box medical algorithms. Science translational medicine 10, 471 (2018), eaao5333.

[21]

Moirangthem Tiken Singh, Abdur Razzaq Fayjie, and Biswajeet Kachari. 2015. Speech Recognition System for North-East Indian Accent. In International Journal of Applied Information Systems (IJAIS). Vol. 9. Citeseer.

[22]

Qianwen Wang, Yao Ming, Zhihua Jin, Qiaomu Shen, Dongyu Liu, Micah J Smith, Kalyan Veeramachaneni, and Huamin Qu. 2019. Atmseer: Increasing transparency and controllability in automated machine learning. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. ACM, 681.

Digital Library

[23]

Yanli Zheng, Richard Sproat, Liang Gu, Izhak Shafran, Haolang Zhou, Yi Su, Daniel Jurafsky, Rebecca Starr, and Su-Youn Yoon. 2005. Accent detection and speech recognition for shanghai-accented mandarin. In Ninth European Conference on Speech Communication and Technology.

Cited By

da Silva TFurtado VFurtado EMendes MAlmeida VSales L(2022)How Do Illiterate People Interact with an Intelligent Voice Assistant?International Journal of Human–Computer Interaction10.1080/10447318.2022.212121940:3(584-602)Online publication date: 22-Sep-2022
https://doi.org/10.1080/10447318.2022.2121219
Carvalho LSuzano JPereira RSantoro FOliveira JMonteiro Ida Hora Rodrigues Kde Gois Ribeiro Darin TFreire AMota M(2021)EthicsProceedings of the XX Brazilian Symposium on Human Factors in Computing Systems10.1145/3472301.3484324(1-12)Online publication date: 18-Oct-2021
https://dl.acm.org/doi/10.1145/3472301.3484324
Guerino GValentim NSantos CBento Villela MGasparini IUchôa Conte T(2020)"Is anybody there?"Proceedings of the 19th Brazilian Symposium on Human Factors in Computing Systems10.1145/3424953.3426649(1-6)Online publication date: 26-Oct-2020
https://dl.acm.org/doi/10.1145/3424953.3426649
Show More Cited By

Index Terms

Discrimination analysis of intelligent voice assistants
1. Human-centered computing
  1. Human computer interaction (HCI)
    1. Empirical studies in HCI
    2. HCI design and evaluation methods
      1. Laboratory experiments
      2. User studies

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

IHC '19: Proceedings of the 18th Brazilian Symposium on Human Factors in Computing Systems

October 2019

679 pages

ISBN:9781450369718

DOI:10.1145/3357155

General Chairs:
Rodrigo Laiola Guimaraes
Universidade Federal do Espirito Santo (UFES)
,
Celso Alberto Saibel Santos
Universidade Federal do Espirito Santo (UFES)
,
Program Chairs:
Vagner Figueredo de Santana
IBM Research
,
Artur Kronbauer
Universidade Salvador (UNIFACS)

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SBC: Brazilian Computer Society

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 October 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

IHC '19

Sponsor:

SBC

IHC '19: XVIII Brazilian Symposium on Human Factors in Computing Systems

October 22 - 25, 2019

Espírito Santo, Vitória, Brazil

Acceptance Rates

IHC '19 Paper Acceptance Rate 56 of 165 submissions, 34%;

Overall Acceptance Rate 331 of 973 submissions, 34%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
182
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 02 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

da Silva TFurtado VFurtado EMendes MAlmeida VSales L(2022)How Do Illiterate People Interact with an Intelligent Voice Assistant?International Journal of Human–Computer Interaction10.1080/10447318.2022.212121940:3(584-602)Online publication date: 22-Sep-2022
https://doi.org/10.1080/10447318.2022.2121219
Carvalho LSuzano JPereira RSantoro FOliveira JMonteiro Ida Hora Rodrigues Kde Gois Ribeiro Darin TFreire AMota M(2021)EthicsProceedings of the XX Brazilian Symposium on Human Factors in Computing Systems10.1145/3472301.3484324(1-12)Online publication date: 18-Oct-2021
https://dl.acm.org/doi/10.1145/3472301.3484324
Guerino GValentim NSantos CBento Villela MGasparini IUchôa Conte T(2020)"Is anybody there?"Proceedings of the 19th Brazilian Symposium on Human Factors in Computing Systems10.1145/3424953.3426649(1-6)Online publication date: 26-Oct-2020
https://dl.acm.org/doi/10.1145/3424953.3426649
Ribeiro KSantos CBento Villela MGasparini IUchôa Conte T(2020)A gender analysis of interaction in online work meeting toolsProceedings of the 19th Brazilian Symposium on Human Factors in Computing Systems10.1145/3424953.3426647(1-6)Online publication date: 26-Oct-2020
https://dl.acm.org/doi/10.1145/3424953.3426647

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten