[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.

Content

Author and article information

Contributors

Stina Hasse Jørgensen

Alice Emily Baird

Frederik Tollund Juutilainen

Mads Pelt

Nina Cecilie Højholdt

Conference

Publication date: May 2018

Publication date (Print): May 2018

Pages: 1-8

Affiliations

[1 ] University of Copenhagen, Department of Arts and Cultural Studies

Karen Blixens Vej 1, 2300

Copenhagen S, Denmark

[2 ] Augsburg University, Chair of Embedded Intelligence for Health Care and Wellbeing, Eichleitnerstr. 30, F2, 86159 Augsburg, Germany

[3 ] University of Copenhagen, Department of Nordic Studies and Linguistics, Karen Blixens Vej 1, 2300

Copenhagen S, Denmark

[4 ] Netcompany, Grønningen 17, 1270

København K, Denmark

[5 ] Malmö University, K3 Arts and Communication, Interaction Design, östra Vervsgatan 11A, 211 19 Malmö, Sweden

Article

DOI: 10.14236/ewic/EVAC18.41

SO-VID: 15f1eb62-e6b6-49c7-94ef-b84a81349970

License:

This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Conference name: Politics of the Machines - Art and After

Conference acronym: EVA Copenhagen

Conference number: 7

Conference location: Aalborg University, Copenhagen, Denmark

Conference date: 15 - 17 May 2018

Conference sponsor: Electronic Workshops in Computing (eWiC)

Conference theme: Digital arts and culture

History

Product

1477-9358 BCS Learning & Development

Self URI (article page): https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/EVAC18.41

Self URI (journal page): https://ewic.bcs.org/

References

Amazon 2017a Start Building on AWS Today Amazon Web Services Available from: https://aws.amazon.com/ 4 June 2018
Amazon 2017b Amazon S3. Amazon Web Services Available from: https://aws.amazon.com/s3/ 3 June 2018
Amazon 2017c Amazon EC2. Amazon Web Services Available from: https://aws.amazon.com/ec2/ 4 June 2018
A BairdS.H. JørgensenE. Parada-CabelieroS HantkeN. CumminsB. Schuller 2017 Perception of Paralinguistic Traits in Synthesized Voices Proceedings of the 12th International Audio Mostly Conference on Augmented and Participatory Sound and Music Experiences (AM 2017) London, UK 23 25 August 2017 New York, USA ACM. No pagination
A BairdS.H. JørgensenE. Parada-CabelieroS HantkeN. CumminsB. Schuller 2018 The Perception of Vocal Traits in Synthesized Voices: Age, Gender, and Human-Likeness The Journal of Audio Engineering Society, Special Issue on Augmented and Participatory Sound and Music Interaction using Semantic Audio 66 4 277 285
R. Barra-ChicoteJ. YamagishiS. KingJ. M. MonteroJ. Macias-Guarasa 2010 Analysis of statistical parametric and unit selection speech synthesis systems applied to emotional speech. Speech Communication 52 5 394 404
J Butler 1993 Bodies that Matter New York Routledge
N L CliffordKwan Min 2000 Does Computer- generated Speech Manifest Personality? An Experimental Test of Similarity-attraction Proceeding of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’00) New York, USA ACM 329 336
Mozilla Corporation 2017 Project Common Voice.Mozilla Corporation Available from: https://voice.mozilla.org/da 4 June 2018
T DutoitH. Leich 1993 MBR-PSOLA: Text-To-Speech synthesis based on an MBE re-synthesis of the segments database Speech Communication 13 3 4
S FeinbergM. Murphy 2000 Applying CognitiveLoad Theory to the Design of Web-based Instruction Proceeding of the 18th Annual ACM International Conference on Computer Documentation: Technology & Teamwork (SIGDOC ’00) Cambridge, USA IEEE 353 360
FestVox 2014a Building Synthetic Voices:Building Prosodic Models FestVox Available from: http://festvox.org/bsv/c1639.html 4 June 2018
FestVox 2014b Building Synthetic Voices: Corpus Development. FestVox Available from: http://festvox.org/bsv/c2176.html 4 June 2018
FestVox 2014c CMU Arctic. FestVox Avaialble from: http://festvox.org/cmu_arctic/cmuarctic.data 4 June 2018
R Gagnon 1978 Votrax real time hardware for phoneme synthesis of speech Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’78) Tulsa, Oklahoma, USA. Cambridge, USA IEEE no pagination
S Hall 1994 Cultural Identity and Diaspora Patrick WilliamsLaura Chrisman Cultural Identity and Diaspora. In Colonial Discourse and Post-Colonial Theory: A reader New York Columbia University Press 392 404
AJ HuntA.W. Black 1996 Unit selection in a concatenative speech synthesis system using a large speech database Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’96) Atlanta, GA, USA. Cambrigde, USA IEEE 1520 6149
L Huybrechts 2014 Participation Is Risky: Approaches to Joint Creative Processes Amsterdam Valiz
A IidaN. CampbellF. HiguchiM. Yasumura 2003 A corpus-based speech synthesis system with emotion Speech Communication 40 1-2 161 187
A Jones 2012 Seeing Differently: A history and theory of identification and the visual arts New York Routledge
T Phan 2017 The Materiality of the Digital and the Gendered Voice of Siri. Transformations 29 23 33
I SaratxagaE. NavasI. HernáezI. Luengo 2006 Designing and recording an emotional speech database for corpus based synthesis in Basque Proceedings of 5th international conference on Language Resources and Evaluation (LREC’06) Genoa, Italy. Luxemburg European Language Resources Association (ELRA) 2126 2129
M. R. Schroeder 1966 Vocoders: Analysis and synthesis of speech. The Bell System Technical Journal 54 5 720 734
G. E. PetersonW. WangE. Sivertsen 1958 Segmentation techniques in speech synthesis The Journal of the Acoustical Society of America 30 739 742
Y TabetM. Boughazi 2011 Speech synthesis techniques. A survey Proceedings of 7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA’11) Tipaza, Algeria. Cambridge, USA IEEE No pagination
W Ward 1989 Understanding Spontaneous Speech Proceeding of the Workshop on Speech and Natural Language (HLT ’89) Stroudsburg, PA, USA Association for Computational Linguistics 137 141
S. J. Young 1979 Speech synthesis from concept: A method for speech output from information systems The Journal of the Acoustical Society of America 66 3 685
H ZenA. SeniorM. Schuster 2013 Statistical parametric speech synthesis using deep neural networks Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’13) Vancouver, BC, Canada. Cambridge USA IEEE No pagination
A.V. D. OordS. DielemanH. ZenK. SimonyanO. VinyalsA. GravesN. KalchbrennerA. SeniorK. Kavukcuoglu 2016 Wavenet A generative model for raw audio arXiv, 1609:03499 Google DeepMind London, UK

Comments

Comment on this article

[1] Amazon 2017a Start Building on AWS Today Amazon Web Services Available from: https://aws.amazon.com/ 4 June 2018

[2] Amazon 2017b Amazon S3. Amazon Web Services Available from: https://aws.amazon.com/s3/ 3 June 2018

[3] Amazon 2017c Amazon EC2. Amazon Web Services Available from: https://aws.amazon.com/ec2/ 4 June 2018

[4] A BairdS.H. JørgensenE. Parada-CabelieroS HantkeN. CumminsB. Schuller 2017 Perception of Paralinguistic Traits in Synthesized Voices Proceedings of the 12th International Audio Mostly Conference on Augmented and Participatory Sound and Music Experiences (AM 2017) London, UK 23 25 August 2017 New York, USA ACM. No pagination

[5] A BairdS.H. JørgensenE. Parada-CabelieroS HantkeN. CumminsB. Schuller 2018 The Perception of Vocal Traits in Synthesized Voices: Age, Gender, and Human-Likeness The Journal of Audio Engineering Society, Special Issue on Augmented and Participatory Sound and Music Interaction using Semantic Audio 66 4 277 285

[6] R. Barra-ChicoteJ. YamagishiS. KingJ. M. MonteroJ. Macias-Guarasa 2010 Analysis of statistical parametric and unit selection speech synthesis systems applied to emotional speech. Speech Communication 52 5 394 404

[7] J Butler 1993 Bodies that Matter New York Routledge

[8] N L CliffordKwan Min 2000 Does Computer- generated Speech Manifest Personality? An Experimental Test of Similarity-attraction Proceeding of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’00) New York, USA ACM 329 336

[9] Mozilla Corporation 2017 Project Common Voice.Mozilla Corporation Available from: https://voice.mozilla.org/da 4 June 2018

[10] T DutoitH. Leich 1993 MBR-PSOLA: Text-To-Speech synthesis based on an MBE re-synthesis of the segments database Speech Communication 13 3 4

[11] S FeinbergM. Murphy 2000 Applying CognitiveLoad Theory to the Design of Web-based Instruction Proceeding of the 18th Annual ACM International Conference on Computer Documentation: Technology & Teamwork (SIGDOC ’00) Cambridge, USA IEEE 353 360

[12] FestVox 2014a Building Synthetic Voices:Building Prosodic Models FestVox Available from: http://festvox.org/bsv/c1639.html 4 June 2018

[13] FestVox 2014b Building Synthetic Voices: Corpus Development. FestVox Available from: http://festvox.org/bsv/c2176.html 4 June 2018

[14] FestVox 2014c CMU Arctic. FestVox Avaialble from: http://festvox.org/cmu_arctic/cmuarctic.data 4 June 2018

[15] R Gagnon 1978 Votrax real time hardware for phoneme synthesis of speech Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’78) Tulsa, Oklahoma, USA. Cambridge, USA IEEE no pagination

[16] S Hall 1994 Cultural Identity and Diaspora Patrick WilliamsLaura Chrisman Cultural Identity and Diaspora. In Colonial Discourse and Post-Colonial Theory: A reader New York Columbia University Press 392 404

[17] AJ HuntA.W. Black 1996 Unit selection in a concatenative speech synthesis system using a large speech database Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’96) Atlanta, GA, USA. Cambrigde, USA IEEE 1520 6149

[18] L Huybrechts 2014 Participation Is Risky: Approaches to Joint Creative Processes Amsterdam Valiz

[19] A IidaN. CampbellF. HiguchiM. Yasumura 2003 A corpus-based speech synthesis system with emotion Speech Communication 40 1-2 161 187

[20] A Jones 2012 Seeing Differently: A history and theory of identification and the visual arts New York Routledge

[21] T Phan 2017 The Materiality of the Digital and the Gendered Voice of Siri. Transformations 29 23 33

[22] I SaratxagaE. NavasI. HernáezI. Luengo 2006 Designing and recording an emotional speech database for corpus based synthesis in Basque Proceedings of 5th international conference on Language Resources and Evaluation (LREC’06) Genoa, Italy. Luxemburg European Language Resources Association (ELRA) 2126 2129

[23] M. R. Schroeder 1966 Vocoders: Analysis and synthesis of speech. The Bell System Technical Journal 54 5 720 734

[24] G. E. PetersonW. WangE. Sivertsen 1958 Segmentation techniques in speech synthesis The Journal of the Acoustical Society of America 30 739 742

[25] Y TabetM. Boughazi 2011 Speech synthesis techniques. A survey Proceedings of 7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA’11) Tipaza, Algeria. Cambridge, USA IEEE No pagination

[26] W Ward 1989 Understanding Spontaneous Speech Proceeding of the Workshop on Speech and Natural Language (HLT ’89) Stroudsburg, PA, USA Association for Computational Linguistics 137 141

[27] S. J. Young 1979 Speech synthesis from concept: A method for speech output from information systems The Journal of the Acoustical Society of America 66 3 685

[28] H ZenA. SeniorM. Schuster 2013 Statistical parametric speech synthesis using deep neural networks Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’13) Vancouver, BC, Canada. Cambridge USA IEEE No pagination

[29] A.V. D. OordS. DielemanH. ZenK. SimonyanO. VinyalsA. GravesN. KalchbrennerA. SeniorK. Kavukcuoglu 2016 Wavenet A generative model for raw audio arXiv, 1609:03499 Google DeepMind London, UK

Celebrating 65 years of The Computer Journal - free-to-read perspectives - bcs.org/tcj65