Best Practice in Voice User Interface Design , speech recognition applications, mobile voice-to-text applications; updates in New Technologies including Social Media
TEDxManchester took place on Monday 13th February this year at one of the iconic Manchester locations – and my “local” – the Cornerhouse. Among the luminary speakers were people I have always been admiring, such as the radio Goddess Mary Anne Hobbs, and people I have become very close friends with over the years – which has led me to an equal amount of admiration, such as Ian Forrester (@cubicgarden to most of us). You can check out their respective talks, as well as some awesome others, in my TEDxManchester report below.
My TEDxManchester talk
I spoke about the weird and wonderful world of Voice Recognition (“Voice Recognition FTW!”): from the inaccurate – and far too often funny – simple voice-to-text apps and dictation systems on your smartphones, to the most frustrating automated Call Centres, to the next generation, sophisticated SIRI and everything in-between. I explained why things go wrong and when things can go wonderfully right. The answer is “CONTEXT”; the more you have of it , the more accurate and relevant the interpretation of user intention will be, and the more relevant and impressive the system reaction / reply will be.
2012 can easily be dubbed the year of TEDx for me, as by mid-February I had already attended two TEDx events! First up was TEDxSalford in late January, where I was just a mindblown attendee, and two weeks later it was TEDxManchester where I had the honour to be a speaker!
TEDxManchester took place on Monday 13th February this year at one of the iconic Manchester locations – and my “local” – the Cornerhouse. Among the luminary speakers were people I have always been admiring, such as the radio Goddess Mary Anne Hobbs, and people I have become very close friends with over the years – which has led me to an equal amount of admiration, such as Ian Forrester (@cubicgarden to most of us).
Here are their respective talks at TEDxManchester 2012 for you to get a taste of the atmosphere at the event and of the impact of the ideas and the immediacy of the sentiments circulated!
I spoke about the weird and wonderful world of Voice Recognition (“Voice Recognition FTW!”): from the inaccurate – and far too often funny – simple voice-to-text apps and dictation systems on your smartphones, to the most frustrating automated Call Centres, to the next generation, sophisticated SIRI and everything in-between. I explained why things go wrong and when things can go wonderfully right. The answer is “CONTEXT”; the more you have of it , the more accurate and relevant the interpretation of user intention will be, and the more relevant and impressive the system reaction / reply will be.
@ar3toul4ki 15 Feb RT @global_lingo: Maria Aretoulaki on voice recognition software. Will digital transcription ever be any good? #tedxmcr no, no it won’t
Lynne McCadden @lmccadden 14 Feb
Belated I know but many congrats to @herbkim for a fantastic TEDxMCR yesterday been thinking about some of it all day today !
Retweeted by @ar3toul4ki
TEDxManchester @TEDxManchester 14 Feb
Here’s to the #TEDxMCR speakers in Session 2 – @daveerasmus @martinsfp @ar3toul4ki @cubicgarden @brendandawes
Retweeted by @ar3toul4ki
TEDxManchester @TEDxManchester 13 Feb
Thanks to @BandXMedia all today’s #TEDxMCR talks were recorded, will be edited & put online soon #TEDxMCR @s2martin
Retweeted by @ar3toul4ki
Lynne McCadden @lmccadden 13 Feb
#tedxmcr learning about quarks and leptons from @tarashears making particle physics easy – sort of
Retweeted by @ar3toul4ki
How to Wreck a Nice Beach @TEDxManchester #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb Luke Robert Mason @LukeRobertMason
It’s a bright future if you are an algorithm or infomorph #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb Luke Robert Mason @LukeRobertMason
@RichardMichie A little bit of non-human agency can’t hurt… Or can it #TEDxMCH
Retweeted by @ar3toul4ki
In reply to RichardMichie
13 Feb Ian Forrester @cubicgarden
Infomorphs or a weaver… #TEDxMCR love the idea very cool! They could work with #perceptivemedia yfrog.com/gzeg2jij
Retweeted by @ar3toul4ki
13 Feb
Ian Pettigrew @KingfisherCoach
#TEDxMCR @skeuomorphology challenging ‘necessity is the mother of invention’; cars weren’t invented as a response to a shortage of horses!
Retweeted by @ar3toul4ki
13 Feb Luke Robert Mason @LukeRobertMason
Pure information technologies are the first evolutionary aware technologies. They are stochastic… Emerge from randomness #TEDxMCR @weavrs
Retweeted by @ar3toul4ki
13 Feb Luke Robert Mason @LukeRobertMason
Living software ‘bots’ or infomorphs via @weavrs #infomorph #TEDxMCR @skeuomorphology
Retweeted by @ar3toul4ki
13 Feb Michael Di Paola @MichaelDiPaola
Robots made from programmable gel…where the hell am I? A parallel universe, the future. No. Just at #TEDxMCR listening to Dan O’Hara
Retweeted by @ar3toul4ki
13 Feb Luke Robert Mason @LukeRobertMason
Infomorph, a form that exists just of information @skeuomorphology #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
Luke Robert Mason @LukeRobertMason
Another type of software agent that exhibits life, @weavrs #infomorph @skeuomorphology #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki
@pgaval δε πειράζει, θα είναι στο YouTube για πάντα! (Μαμά! )
In reply to Petros Gavalakis
13 Feb
@ar3toul4ki
Mondays are my favourite days of the week : D
13 Feb Matthew Brooks @brooksoid
Great, great talk by @brendandawes on the value of pursuing ideas, and the ideas they spawn, without necessarily knowing where you’re going
Retweeted by @ar3toul4ki
from Manchester, Manchester
13 Feb RichardMichie @RichardMichie
Failed art at school? You can still exhibit at #moma @brendandawes #tedxmcr great story love it
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
@brendandawes’ cinema redux of Hitchcock’s Vertigo #TEDxMCR twitpic.com/8jfs95
13 Feb
sphey1 @sphey1
If you make something, give it a name – re: Cinema Redux @brendandawes #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
Things that @brendandawes has done with his 3-printer #TEDxMCR twitpic.com/8jfpn6
13 Feb
@ar3toul4ki
@brendandawes : the creative process is iterative. ( but Battling it against time & cost constraints) #TEDxMCR
13 Feb @ar3toul4ki
RT @CMindsKelly: @brendandawes. The thing we in the room all share is curiosity. That’s why we’re always making new things #TEDxMCR”
13 Feb Martin Bryant @MartinSFP
At #tedxmcr, @cubicgarden explained how @tdobson and @adew saved his life. instagr.am/p/G9BmXRStoc/
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki
Ian Forrester: fear the fear #TEDxMCR
13 Feb Claire-Marie @CMBoggiano
‘We are complex & unique organisms And yes, I am still an atheist.’ Ian Forrester, #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
Indeed! RT @TonyChurnside: @cubicgarden really touching. Very nicely done!
13 Feb @ar3toul4ki
@brooksoid any time!
In reply to Matthew Brooks
13 Feb Matthew Brooks @brooksoid
@ar3toul4ki great talk Maria, speech recog in focus at the beeb right now, be interesting to talk once I’ve worked out what our landscape is
Retweeted by @ar3toul4ki
13 Feb TEDxManchester @TEDxManchester
Link to the funny vid played by @ar3toul4ki – Scottish voice recognition problems.. http://youtu.be/sAz_UvnUeuU
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
Ευχαριστώ! Το είδες μήπως; RT @pgaval: @ar3toul4ki Καλή επιτυχία!
13 Feb Claire-Marie @CMBoggiano
‘When I was lying in bed dying, where were the real people?’ Ian Forrester, #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb Tony Churnside @TonyChurnside
Watching @cubicgarden talk about his #brushwithdeath. A very scary time. #TEDxMCR pic.twitter.com/hED5mimw
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki
@tdobson @cubicgarden is talking about you! : D
In reply to Tim Dobson
13 Feb Tim Dobson @tdobson
so @cubicgarden is talking about it #brushwithdeath when I may or may not have been his flatmate at the time.. #tedxman
Retweeted by @ar3toul4ki
13 Feb Matthew Brooks @brooksoid
And @cubicgarden ‘s talk is about… @cubicgarden ! He’s finally gone recursive. #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb Tony Churnside @TonyChurnside
@cubicgarden you’re looking good! pic.twitter.com/n8xvkzJB
Retweeted by @ar3toul4ki
13 Feb
Ian Forrester @cubicgarden
And next on at #TEDxMCR its @ianforrester. With the story of me…
Retweeted by @ar3toul4ki
13 Feb TEDxManchester @TEDxManchester
Hilarious talk on Voice Recognition from Dr Maria Aretoulaki #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb Tim Dobson @tdobson
@davemee it’s all about context! /cc @ar3toul4ki
Retweeted by @ar3toul4ki
In reply to Dave Mee
13 Feb Tim Dobson @tdobson
@davemee @ar3toul4ki “fetish cheese”
Retweeted by @ar3toul4ki
In reply to Dave Mee
13 Feb Dave Mee @davemee
@tdobson @ar3toul4ki feed her through siri and send me a transcript!
Retweeted by @ar3toul4ki
In reply to Tim Dobson
13 Feb Kate Towey @katiemaymanc
Fascinating talk from Tara Shears on particle physics. ’2012 is year of the Higgs’ #tedxmcr
Retweeted by @ar3toul4ki
13 Feb Ian Pettigrew @KingfisherCoach
So far at #TEDxMCR we’ve covered pursuing your passion, JDI (and make mistakes), technology, algorithms, and particle physics. I’m happy!
Retweeted by @ar3toul4ki
13 Feb Allie Johns @AllieJohns
I propose bringing back Tomorrow’s World and having Tara Shears present it #tedxmcr
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
@TaraShears @TEDxManchester: oh my Higgs! We’ve seen something! Or have we?? #TEDxMCR twitpic.com/8jdo56
13 Feb
Ian Forrester @cubicgarden
The goddamn particle explained at #TEDxMCR yfrog.com/obsv5tmj
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki
@TaraShears @TEDxManchester: where’s that God-damned Higgs particle?! If we don’t find it, we’ll have to start all over again… #TEDxMCR
13 Feb Claire-Marie @CMBoggiano
“@lmccadden: #tedxmcr learning about quarks and leptons from @tarashears making particle physics easy – sort of”
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
@TaraShears @TEDxManchester: symmetry, simplicity, elegance = beauty of the standard model of particle physics #TEDxMCR
13 Feb TEDxManchester @TEDxManchester
Up next @TEDxManchester is @TaraShears – tune in live to ow.ly/92eRf #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
@TEDx video 1 @TEDxManchester: pragmatic chaos to describe fluid things such as culture #TEDxMCR
13 Feb @ar3toul4ki
@coralgrainger no worries sweetness : )
In reply to coralgrainger
13 Feb @ar3toul4ki
@TEDx video @TEDxManchester: what we don’t understand, we give a name and a story to #TEDxMCR
13 Feb @ar3toul4ki
@maryannehobbs you were, nay ARE, awesome! Xx
In reply to maryanne hobbs
13 Feb @ar3toul4ki
Dan O’Hara @skeuomorphology @TEDxManchester: from random relentless replication (cf. spambots) to guided transformation of chaos #TEDxMCR
13 Feb Kim Willis @KimberleyWillis
Dan O’Hara: technology is not a selection of gadgets but a body of knowledge instagr.am/p/G8sGbrBVY7/ #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
Ian Wareing @ianwareing
#tedxmcr @skeuomorphology “Necessity is not the mother of invention. Invention is the mother of necessity”
Retweeted by @ar3toul4ki
13 Feb Ian Forrester @cubicgarden
Bloatware… or stimulation of the real on the virtual RT @maanasvarun: Skeumorphism. wait what? #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
Dan O’Hara @skeuomorphology @TEDxManchester: the creation of living technology by merging the Arts and Sciences #TEDxMCR
13 Feb @ar3toul4ki
@maryannehobbs @TEDxManchester: John Peel saving lives again #TEDxMCR
13 Feb @ar3toul4ki
@maryannehobbs @TEDxManchester: follow your passion! #TEDxMCR twitpic.com/8jcwpn
13 Feb
TEDxManchester @TEDxManchester
Hi all we’re suggesting #TEDxMCR as the hashtag for the event today as it’s a bit shorter than #TEDxManchester
Retweeted by @ar3toul4ki
13 Feb TEDxManchester @TEDxManchester
Sorry folks for the livestream #fail. We’re currently on this channel live.. bit.ly/y9kkZa #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
@gazshaw cheers!
In reply to Gaz Shaw
13 Feb @ar3toul4ki
see you there Mike! It’s been a loooong time! RT @mike_higham: @ar3toul4ki @TEDxManchester Looking forward to it #TEDxMCR
13 Feb @ar3toul4ki
@heloukee oh nooo : s
In reply to Helen Keegan
13 Feb @ar3toul4ki
Excited & honoured to be speaking @TEDxManchester today. My talk “Voice Recognition FTW!” on the present+future of user interfaces #TEDxMCR
13 Feb @ar3toul4ki
See you there Matt! RT @matthbooth: A bit of work then @TEDxManchester. Looking forward to it.
13 Feb Allie Johns @AllieJohns
“@maryannehobbs: interesting day: speaking about passion at @TEDxManchester 1pm.. ” > we can never have enough passion in our lives.
Retweeted by @ar3toul4ki
13 Feb @ar3toul4ki
Will you be my groupie?? RT @technicalfault: @ar3toul4ki Dr Maria at TEDx!
12 Feb @ar3toul4ki
Looking forward to giving #TEDxMCR an insight into the wondrous+often misconstrued world of voice recognition @TEDxManchester tomorrow
12 Feb TEDxManchester @TEDxManchester
And in other late-breaking news Dr. Maria @Ar3toul4ki will also be taking the stage tomorrow at #TEDxMCR
Retweeted by @ar3toul4ki
12 Feb TEDxManchester @TEDxManchester
A big welcome for our latest speaker @MartinSFP – European Editor @TheNextWeb for #TEDxMCR. Like @MaryAnneHobbs a brave no-slide presenter!
Retweeted by @ar3toul4ki
11 Feb Anna Nachesa @ashalynd
I’ll probably be very evil if I ask during an interview if tail-optimized recursion is possible in C. OTOH, it might be a great icebreaker:)
Retweeted by @ar3toul4ki
11 Feb @ar3toul4ki
“The overall emphasis of the workshop is on the contribution of cognitive science to language processing, including conceptualisation, representation, discourse processing, meaning construction, ontology building, and text mining.”
There have been NLPCS Workshops in Porto (2004), Miami (2005), Paphos (2006), Funchal (2007), Barcelona (2008), Milan (2009) and Funchal (2010).
Copenhagen Business School
This year’s 8th International NLPCS Workshop just took place this weekend in Copenhagen, Denmark (20-21 Aug 2011). The Workshop topic was: “Human-Machine Interaction in Translation“, focussing on all aspects of human and machine translation, and human-computer interaction in translation, including: translators’ experiences with CAT tools, human-machine interface design, evaluation of interactive machine translation, user simulation and human factors. Thus, the topics were approached from a number of different perspectives:
from full automation by machines for machine (traditional NLP or HLT)
semi-automated processing, i.e. machine-mediated processing (programs assisting people in their tasks),
but also simulation of human cognitive processes
I had the opportunity once again to review a few of the paper submissions and can therefore highly recommend reading the full Proceedings of the NLPCS 2011 Workshop that have just been made available.
I found particularly interesting the following 3 contributions:
Valitutti, A. “How Many Jokes are Really Funny? A New Approach to the Evaluation of Computational Humour Generators”
Nilsson, M. and J. Nivre. “Entropy-Driven Evaluation of Models of Eye Movement Control in Reading”
and
Finch, A., Song, W., Tanaka-Ishii, K. and E. Sumita. “Source Language Generation from Pictures for Machine Translation on Mobile Devices”
“improve the human condition by advancing the discipline of Interaction Design”
A very worthy cause indeed, especially since it is true that “the human condition is increasingly challenged by poor experiences. “!
Today’s Joint Workshop in New York aims to bring together interaction design practitioners from across the voice, interactive, and digital areas to identify the issues and challenges involved in speech interaction design on mobile devices, such as smartphones and tablets, and to come up by the end of the day with ways to approach them or even tackle them. A very ambitious format that, however, really does work!
And if you don’t manage to take part in today’s workshop, make sure you go to the SpeechTEK Conference and Exhibition itself that starts tomorrow and runs until Wednesday the 10th. Listen to presentations and see or even try for yourself market-ready products relating to:
multimodal applications
cross-channel applications
speech analytics
speaker identification and verification
in-car systems
natural language and say-anything technologies
speech translation
voice-enabled personal assistants
as well as the latest speech recognition techniques and technologies
I particularly recommend the Keynote Panel on “Mobility — A Game-Changer for Speech?” on Tuesday on how smartphones are dramatically changing how customers interact with businesses and with the devices themselves. Some really interesting issues and questions will be raised, such as:
* How voice user interfaces will be integrated with graphical user interfaces?
or
* Will users embrace voice as they have embraced keypads on mobile devices?
Sadly I am in the UK today and next week, so I’m going to miss it all. But if you are lucky enough to be in or near New York, make sure you go and enjoy!
I promised some time ago to put up the slides of my presentation at this year’s SpeechTEK Europe 2010 in London, the first SpeechTEK to have taken place outside of the US. My presentation, “The Eternal Battle Between the VUI Designer and the Customer“, was on Wednesday 26th May 2010 and opened the “Voice User Interface Design: Major Issues” Session. It went down really well, and I had afterwards several people in the audience tell me about their own experience and asking me for tips on how to deal with similar issues.
Here is a PDF with the presentation slides:
Maria Aretoulaki – “The Eternal Battle Between the VUI Designer and the Customer” (SpeechTEK Europe 2010 presentation)
VUI Design is preoccupied with the conception, the design, the implementation, the testing, and the tuning of solutions that work in the most efficient, secure and non-irritating for the user manner. Well, realistically that’s what VUI Design can achieve. In an ideal world, the VUI Designer would actually strive to create speech applications that – apart from taking into consideration the customer’s financial and brand requirements – would also fit the caller’s needs, goals and preferences. The initial Requirements analysis should bring both in focus. So much is already known and accepted both amidst the VUI Designers and the customers.
The problems start just after they all leave the meeting room and start working on the implementation: Call flow design, system persona development and prompt crafting, but even recognition grammars, all seem to fall victim of a war of words and attitudes between the VUI Design expert who has seen systems being developed and spurned before, and the customer with his tech-savvy business team and their technical architects and programming geniuses, who all think they know what callers want and how call flows should be structured, prompt wording crafted and grammars written, just because they have got strong opinions! Even the results of Usability tests are liable to different interpretations by each side.
This presentation pinpoints common pitfalls in the communication between a VUI Designer and customer employees and recommends ways to resolve conflicts and disagreements on the application design and implementation.
Credits:
SpeechTEK Europe 2010 was organised by:
Information Today, Inc. 143 Old Marlton Pike Medford NJ 08055 U.S.A. Phone 1 (609) 654-6266. http://www.infotoday.com
Just back from SpeechTEK Europe 2010, the first SpeechTEK to take place outside of the US, which was great fun. I gave a presentation on “The Eternal Battle Between the VUI Designer and the Customer“, which went down quite well (more on that in my next blog), heard many interesting new ideas about how normal people view normal communication channels to a company or organisation (the Web is prevailing but multimodality and crosschannel communication will be indispensable in a couple of years), heard about new applications of speech and touchtone and any challenges they are facing, and met up with loads of people I know in the field from companies I’ve worked for and cities I have worked in. I have started a few projects and collaborations as a result (again to be announced in my next blog), but for now I would like to share my presentation at SpeechTEK 2007 in New York on Monday 20th August 2007 (how time passes!), entitled: “Does Your Customer Know What They are Signing off?”.
Maria Aretoulaki – SpeechTEK 2007 presentation – opening slide
As it says in the accompanying blurb: “This presentation stresses the importance of incremental and modular descriptions of system functionality for targeted and phased reviews and testing. This strategy ensures clarity, consistency, and maintainability beyond the project lifetime and eliminates the need for changes midproject, thus both managing customer expectations and protecting the service provider from ad-hoc requests.“.
The idea is to have a standardised way to document speech application design both in terms of call flow depictions and in terms of functionality description. In addition, 3 different tiers of functionality and call flow representation are proposed, from the more abstract High-Level design (what range of tasks can a system perform?), to the rather detailed Macro-Level (all the user interaction and back-end processes and their interdependencies), to the very detailed Micro-Level which documents every single condition, system prompt and related recognition grammar.
Maria Aretoulaki – 3-tier speech app design representation
The point is that, in every speech project, a number of people with very different backgrounds, roles and expectations are involved, from the Business-minded, to the Techie, to the Usability expert: from Account Managers to the Marketing Strategists, to the Call Centre Managers, the IT Managers, the System Architects, the Programmers, and the VUI Designer themselves (more on these different characters in my next blog with my SpeechTEK 2010 presentation). The 3 different tiers of speech design representation and documentation are ideal in catering for the diverse information needs of those very different groups. The Business and Marketing guys understand better the High-Level representation with the list of things that the system can do in different cases. The Call Centre Managers and some very involved (and worried!) business guys from the side of the customer feel better when they see the Macro-Level detail, because they feel they have more information and therefore more control over what is being designed and implemented. It is also something very concrete to sign off (and therefore difficult to dispute at will later on). The VUI Designer and the System Architect and the various application developers really need the excruciating detail of the Micro-Level: every single condition (including every case where things go wrong) needs to be documented, along with every different prompt that the system will utter (including when it doesn’t recognise or even hear what the caller says), and every speech recognition grammar that is activated every time the system expects a reaction from the caller / user. The inherent modularity and the incremental nature of the design representation means that it can be more easily maintained, more readily modified, and even more straightforwardly adopted and adapted for other speech and multimodal applications in the future. So everybody’s happy
I gave this presentation when I was Head of Speech Design at Vicorp, although the basic ideas behind it matured during the time I was Senior VUI Designer at Intervoice (now Convergys).
Credits:
SpeechTEK 2007 was organised by:
Information Today, Inc.
143 Old Marlton Pike
Medford NJ 08055 U.S.A.
Phone 1 (609) 654-6266. http://www.infotoday.com
Artificial Neural Networks are back! Excellent. Makes me nostalgic about my PhD days. lnkd.in/etMCsK2 weeks ago
Delighted to be in the Consortium that just got awarded EU funding for a high-risk/high-reward project on multimodal dialogue systems! 1 month ago
Proud to have Raytheon BBN as a client! They just got awarded a 14th Patent on their AVOKE Speech analytics tools! google.com/patents/US8102…1 month ago
#TEDxMCR @s2martin
#TEDxMCH
see you there Mike! It’s been a loooong time! RT @mike_higham: @ar3toul4ki @TEDxManchester Looking forward to it #TEDxMCR
