The Creative Speech Technology Network

Lead Research Organisation: University of York
Department Name: Computer Science

Abstract

People are increasingly expected in every-day like to interact with synthetic voices. These encounters are often not very satisfactory. The suggestion is that a major reason for this is that these voices do not sound 'right'. Synthetic voices have improved greatly in recent years in that they sound more human-like. Yet there remain two (conflicting) problems: On the one hand they are still not entirely human-like; most people spot the fact that they are listening to synthesizer within a few words.At the same time, even if it were possible to re-create a perfectly human-sounding voice, it would convey the wrong associations for what are computer-generated utterances. The computer does not have all of the other attributes of a person, such as intelligence, a sense of humour, empathy etc. Put another way, a computer voice should sound like a computer voice. The question is: how should that sound?The objective of this network is to bring together people who know about (human) voices and how to use and manipulate them - from an artistic background - with technicians who know how to generate synthetic voices. By establishing and developing a language through which these disparate people can communicate, it will be possible to create new voices for specific purposes. The focus of the work will be on creating artistically inspired artefacts which will challenge the potentials of synthetic voice production. Those artefacts will also be used to disseminate the results of the work - to expose it to members of the public. This will share the results of the research as well as allowing the final evaluation of the voices to be given to the people who matter - those who have to put up with this kind of interaction on a daily basis.

Planned Impact

Anyone who interacts with any systems using a synthetic voice should benefit from this work. That could be almost anyone in the current environment, but specific applications would include: call centres, interactive (particularly phone-based) booking and shopping systems, some public announcements (e.g. airports and railway stations), voice-based guides, as used in galleries and museums. Through the commitment to public dissemination, these every-day users will become more aware of the possibilities and to expect better use of speech in their encounters with these systems. Particular benefit should accrue to those who use synthetic speech as a means of expressive communication, usually as a result of their disability. There will also be a benefit to those who rely on synthetic speech as a result of visual impairments. This will be realized mainly through members the network, both academic and industrial. Artists will benefit not only from new possibilities in voice synthesis but also from an enhanced understanding of voice and how it works. New artistic pieces will be created - and exhibited - within the network, but there would also be expected to be new opportunities beyond its existence. Ultimately speech synthesizer manufacturers should benefit from the ability to create better products. Those who research speech synthesis will benefit from new insights which are based on the notion that human verisimilitude is not the only worthy quality. Designers and developers of human-machine interactions will benefit from new possibilities for communication. By the very nature of a network, there will be dissemination within the broad community of interested parties, some of whom have already been identified, others who will be expected to join in with the network when it has been created. The network will be focused on the creation of artefacts which will be the basis of dissemination particularly to the general public, as well as the research community. Other 'traditional' forms of research dissemination - papers, conferences and websites will also be exploited to share the benefits with the research communities beyond the network.

Publications


10 25 50
Alistair Edwards (Co-Author) (2012) Communication Matters, Vol 26, No 3 in Augmentative and Alternative Communication
Arapinis M (2013) Privacy-supporting cloud computing by in-browser key translation in Journal of Computer Security
Christopher Newell (Co-Author) Creative Research into Sound Arts Practice
Edwards AD (2013) Creative Speech Technology: editorial introduction to this special issue. in Logopedics, phoniatrics, vocology
Elsam P (2013) Gwen's crazy little green clowns. in Logopedics, phoniatrics, vocology
Moore R (2013) Your Virtual Butler
Moore R (2016) Vocal Interactivity in-and-between Humans, Animals, and Robots in Frontiers in Robotics and AI
Pauletto S (2013) Exploring expressivity and emotion with artificial voice and speech technologies. in Logopedics, phoniatrics, vocology
 
Title Concert for Human and Artificial Voice 
Description Six concert pieces involving performances by live singers and artificial voices. See crestnetwork.org.uk. 
Type Of Art Performance (Music, Dance, Drama, etc) 
Year Produced 2013 
Impact Featured on Russia 1 TV 
URL http://crestnetwork.org.uk/page/scarborough-concert
 
Title From North to South: A vocal Pi 
Description A performance in which human actors sonified the shifting of the terrestrial magnetic poles over time. 
Type Of Art Performance (Music, Dance, Drama, etc) 
Year Produced 2013 
Impact Positive audience feedback 
 
Title Performance as a part of the York Festival of Ideas 
Description Performance of music from the Concert for Human and Artificial Voices, as a part of the York Festival of Ideas, with Mezzo Soprano Lisa Coates, 24 June 2013, York. 
Type Of Art Performance (Music, Dance, Drama, etc) 
Year Produced 2013 
Impact Unknown 
 
Title Voice by Choice 
Description Short comedy drama 
Type Of Art Film/Video/Animation 
Year Produced 2012 
Impact Live showings plus 1,656 on-line viewings (November 2014) 
URL http://vimeo.com/46831064
 
Description The CreST Network create opportunities for a wide range of people with different interests related to speech technology to work together. It did not have specific technological or theoretical research objectives. It was successful in promoting collaboration and has led to research and creative projects.
Exploitation Route Some may benefit by extending some of the specific outputs of the project (e.g. performances of human and synthesized voices). Others may be able to learn from the ways we were able to successfully promote highly interdisciplinary collaboration.
Sectors Creative Economy,Leisure Activities, including Sports, Recreation and Tourism,Other
URL http://crestnetwork.org.uk
 
Description The approach adopted by the CreST Network included a number of innovative methodologies and as an extreme interdisciplinary network it was driven by cross-disciplinary approaches. By no means a 'talking shop' and with collaborators from arts, science, industry and users, the focus of the Network was on making work to display to both the academic community, the general public and a more specialized public made up of AAC users. These exhibits or artefacts were produced in individual interdisciplinary groups with strict time and budgetary constraints. The resulting roadshow toured to four venues in the North of England and was covered extensively by local, national and international media. See http://crestnetwork.org.uk/page/articulate-media. Much of the equipment developed in order to demonstrate the systems to the wider public was bespoke, including digital and tangible interfaces, games and sensors. Most recently, the live performance for human and synthetic voice, 'Your Call' has received a number of performances (http://www.yourcallopera.com/). This piece originated during the CreST Network and is a collaboration between Network members. Beneficiaries: General public, researchers, artists, disabled people
First Year Of Impact 2011
Sector Creative Economy,Other
Impact Types Cultural,Societal
 
Description IGL sponsorship
Amount £1,000 (GBP)
Organisation IGL Software Engineering 
Sector Private
Country United Kingdom of Great Britain & Northern Ireland (UK)
Start 12/2012 
End 12/2012
 
Description SANM
Amount £400 (GBP)
Organisation Sanmina Corporation 
Sector Private
Country United States of America
Start  
 
Description Context ultra-awareness for AAC 
Organisation State University of New York (SUNY) at Stony Brook
Country United States of America 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact Members of the network - and others - attended
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Aberdeen
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of California
Country United States of America 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None yet.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Dundee
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Edinburgh
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Exeter
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Glasgow
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Malta
Country Malta, Republic of 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Minnesota
Country United States of America 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Neuchatel
Country Switzerland, Swiss Confederation 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet
Start Year 2012
 
Description Context ultra-awareness for AAC 
Organisation University of Tilburg TiU
Country Netherlands, Kingdom of the 
Sector Academic/University 
PI Contribution As a result of discussions within the CreST Network a meeting was held in December 2012 (funded independently). It included a number of CreST members (listed below) and others and started to outline a research proposal to investigate this topic.
Collaborator Contribution Members of the network - and others - attended
Impact None, yet
Start Year 2012
 
Description Speech Synthesis in Extreme Environments 
Organisation Newcastle University
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution Addressing the design challenges inherent in a synthesis system for a person with cerebral palsy, who is unable to speak, performing stand-up comedy. This collaboration develops my contribution to interdisciplinary frameworks for the convergence of arts and science expertises in the design of augmentative and alternative communication devices.
Collaborator Contribution A number of Network members have been involved in this project.
Impact It is anticipated that research proposals will emerge, but they have not yet been put in place.
Start Year 2012
 
Description Training actors for corpus production for speech synthesis systems 
Organisation Toshiba Research Europe Ltd
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Private 
PI Contribution Proving a framework to constrain actors' emotional choices when generating audio recordings for corpus production. An opportunity to develop partnerships in arts and science leading to process and product innovations in the field of emotional speech synthesis. Implementation stage complete (see http://www.bbc.co.uk/news/technology-21827924). Paper in preparation.
Collaborator Contribution This is a collaboration including Network members. It was sparked by the bringing together of technologists and artists (actors) within the Network.
Impact Publications are in preparation.
Start Year 2012
 
Description 'Voice by Choice' - 5-minute film 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Short film: http://vimeo.com/46831064 (1,254 online plays). Main House screening at City Screen, York. Roadshow screeings in Hull, Sheffield and Scarborough. Extracts shown on national and international TV.



As a result of a variety of disabilities, some people are unable to speak using their bodies alone. Some of these people use voice-enabled augmentative and alternative communication (AAC) devices, sometimes called VOCAs. These consist of some form of input interface and generate synthetic speech. The user's choice of voices is very limited, usually constrained to selecting one of a small set of installed 'voices'. The result is that when a number of users get together it can be difficult to know who is speaking at any one time, particularly if there are a number of people using the same voice.



Research: In general, manufacturers of VOCAs do not develop their own computer voices but may choose to integrate some more advanced third-party voices into their systems. This decision is based primarily on technical and commercial considerations. Up until now AAC users, who have the most personal engagement with this technology, have had little involvement in this process. The CreST Network would like to encourage AAC users and computer voice developers to work together.

Live showings plus 1,656 on-line viewings (November 2014)
Year(s) Of Engagement Activity 2012
URL http://vimeo.com/46831064
 
Description Accent the Positive 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? Yes
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Public lecture and demonstratio, staged as part of the York Festival of Ideas, 2013.

Positive feedback from attendees
Year(s) Of Engagement Activity 2013
 
Description Articulate: The Art and Science of Synthetic Speech (Roadshow) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact A series of exhibits, displaying work from the Network were mounted in public spaces. Details: http://crestnetwork.org.uk/.



A number of Network members were involved at different times. Listed below are the main ones.

Large-scale involvement by passing members of the public as well as organized visits from groups including schools.
Year(s) Of Engagement Activity 2012
URL http://crestnetwork.org.uk
 
Description BBC Health Webpage: Speech dating - using a computer voice to find your partner 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact http://www.bbc.co.uk/news/health-20587917.

Unknown. It's a webpage
Year(s) Of Engagement Activity 2012
URL http://www.bbc.co.uk/news/health-20587917
 
Description BBC Radio Five Live interview 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact Interview with Christopher Newell.

Radio broadcast. hard to say
Year(s) Of Engagement Activity 2012
 
Description BBC TV Look North feature 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Television piece on the Network and the Articulate Roadshow.

TV feature
Year(s) Of Engagement Activity 2012
 
Description BBC World Service 'Click' interview 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Alistair Edwards was interviewed in this programme regarding the Network and particularly the Articulate Roadshow.

World Service radio feature/interview. Hard to gauge.
Year(s) Of Engagement Activity 2012
 
Description BBC World Service Digital Planet Facebook Page 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact https://www.facebook.com/groups/4287320286/.

Webpage
Year(s) Of Engagement Activity 2013
URL https://www.facebook.com/groups/4287320286/
 
Description CereProc Brings TTS to the Global CreST Network Tour 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact http://www.speechtechmag.com/Articles/News/Industry-News/CereProc-Brings-TTS-to-the-Global-CreST-Network-Tour--86499.aspx.

It's a webpage
Year(s) Of Engagement Activity 2012
URL http://www.speechtechmag.com/Articles/News/Industry-News/CereProc-Brings-TTS-to-the-Global-CreST-Net...
 
Description CereProc: gives voice to emotion 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact http://www.computescotland.com/cereproc-gives-voice-to-emotion-5653.php.

Unknown
Year(s) Of Engagement Activity 2012
URL http://www.computescotland.com/cereproc-gives-voice-to-emotion-5653.php
 
Description Computers that Talk and Listen. 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Public/other audiences
Results and Impact University of York Public Lecture series.

Public engagement
Year(s) Of Engagement Activity 2012
 
Description Concert for artificial and human voice 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Six concert pieces involving performances by live singers and artificial voices. See crestnetwork.org.uk.

Live performances. Works have been developed and re-presented elsewhere also
Year(s) Of Engagement Activity 2013
 
Description CreST Documentary 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Video documenting the Network. http://www.youtube.com/watch?v=4jDSpk5F2qo&feature=youtu.be.

55 views (November 2014)
Year(s) Of Engagement Activity 2013
URL http://www.youtube.com/watch?v=4jDSpk5F2qo&feature=youtu.be
 
Description From South to North: A vocal pi 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Concert and lecture.

A concert of human and artifical voices, some of which were premiered in the previous concert in Scarborough. Also explanatory talks.

Science in an entertainment
Year(s) Of Engagement Activity 2013
 
Description Human and synthetic voice concert gives Scarborough gallery 'world first' 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact http://www.beautifulnorthyorkshire.com/2013/01/human-and-synthetic-voice-concert-gives.html.

Magazine article
Year(s) Of Engagement Activity 2013
URL http://www.beautifulnorthyorkshire.com/2013/01/human-and-synthetic-voice-concert-gives.html
 
Description Invitation to contribute to World Voice Day 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Invitation to contribute elements of the CreST Roadshow to World Voice Day celebrated at the University of York 16/04/2013.

Public engagement
Year(s) Of Engagement Activity 2013
 
Description Performance as a part of the York Festival of Ideas 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Performance of music from the Concert for Human and Artificial Voices, as a part of the York Festival of Ideas, with Mezzo Soprano Lisa Coates, 24 June 2013, York.

Public performance
Year(s) Of Engagement Activity 2013
 
Description Presentation at NYC Electroacoustic Music Festival 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Presentation of 2 works for the concert for human and artificial voices
http://www.harvestworks.org/apr-4-articulate-speech-technology-in-the-arts-and-science/.

Composers Kevin Jones (U.S.) and Robert MacKay (U.K.) will present an evening of music and discussion about their work with synthetic speech technology as a part of the CreST Network (Creative Speech Technology) at the University of York. CreST is an international collaboration of science and arts practitioners investigating speech synthesis, interactive speech systems and the development of a common language among people in science and the arts.

Unknown
Year(s) Of Engagement Activity 2013
URL http://www.harvestworks.org/apr-4-articulate-speech-technology-in-the-arts-and-science/
 
Description Progress & prospects in spoken language processing 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Presentation at the Institute of Acoustics Speech & Hearing AGM, London.

Scientific presentation to peers
Year(s) Of Engagement Activity 2012
 
Description Sounds of CreST Network The Voice and Technology 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact On-line audio documentary https://soundcloud.com/crestnetwork.

Number of listeners unknown
Year(s) Of Engagement Activity 2013
URL https://soundcloud.com/crestnetwork
 
Description Speaking and Listening Machines: Siri and beyond 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact The Voice Symposium, London Science Museum's Dana Centre.

Public engagement
Year(s) Of Engagement Activity 2012
 
Description Speed dates with computer voices 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact http://www.rocketnews.com/2012/12/speed-dates-with-computer-voices/.

It's a webpage
Year(s) Of Engagement Activity 2012
URL http://www.rocketnews.com/2012/12/speed-dates-with-computer-voices/
 
Description Spoken language processing: where do we go from here? 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Other academic audiences (collaborators, peers etc.)
Results and Impact Seminar at Science and Technology Research Institute, University of Hertfordshire.

University seminar
Year(s) Of Engagement Activity 2012
 
Description Spoken language processing: where do we go from here? 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Professional Practitioners
Results and Impact Seminar at the School of Computer Science, University of Birmingham.

University seminar
Year(s) Of Engagement Activity 2012
 
Description Spoken language processing: where do we go from here? 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Professional Practitioners
Results and Impact Seminar at the University of Lincoln.

Seminar
Year(s) Of Engagement Activity 2012
 
Description TV Broadcast on Russia 1 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Coverage of the Network, concentrating on the Concert for Artificial and Human Voice



Various contributors in addition to those below



http://www.1tv.ru/news/other/225843.

Publicity on Russia 1 TV - which as an audience of 250 million (http://en.wikipedia.org/wiki/Channel_One_Russia)
Year(s) Of Engagement Activity 2013
URL http://www.1tv.ru/news/other/225843
 
Description Talking with Machines 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact The Voice, (public engagement event) Wellcome Collection, London.

Public engagement
Year(s) Of Engagement Activity 2013
 
Description Video recordings of Network meetings 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact All meetings were recoded on video and are available: http://www.livestream.com/crestnetwork.

None of which we are aware
Year(s) Of Engagement Activity 2011
URL http://www.livestream.com/crestnetwork