METALOGUE: Building a Multimodal Spoken Dialogue Tool for teaching Call Centre Agents metacognitive skills

21 Jul

METALOGUE logo

Since November 2013, I’ve had the opportunity to actively participate in the new EU-funded FP7 R & D project, METALOGUE, through my company DialogCONNECTION Ltd, which is one of the 10 Consortium Partners. The project aims to develop a natural, flexible, and interactive Multi-perspective and Multi-modal Dialogue system with metacognitive abilities, i.e. a system that can monitor, reason about, and provide feedback on its own behaviour, intentions and strategies, as well as the dialogue itself, guess those of its interlocutor,  and accordingly plan the next step in the dialogue. The goal is to dynamically adapt both its strategy and its behaviour (speech and non-verbal aspects) in order to influence the interlocutor’s reaction, and hence the progress of the dialogue over time, and thereby also achieve its own goals in the most advantageous way for both sides. The project runs for 3 years (until Oct 2016) and has a budget of € 3,749,000 (EU contribution: € 2,971,000). METALOGUE brings together 10 Academic and Industry partners from 5 EU countries (Germany, Netherlands, Greece, Ireland, and UK).

metalogue_replay

The METALOGUE research focuses on interactive and adaptive coaching situations where negotiation skills play a key role in the decision-making processes. Reusable and customisable software components and algorithms will be developed, tested and integrated into a prototype platform, which will provide learners with a rich and interactive environment that will help them develop metacognitive skills, support motivation, and stimulate creativity and responsibility in the decision-making, argumentation, and negotiation process. The project will produce virtual trainers capable of engaging in natural interaction in English, German, and Greek, using gestures, facial expressions, and body language.

 

Pilot systems will be developed for 2 different Sectors: Government and Industry. The corresponding user scenaria that have been selected are: a) Youth Parliamentarian Debating Skill Tutoring (for the Hellenic Youth Parliament) and b) Call Centre Agent Training (for multilingual UK Call Centres). Particularly for Call Centres, we have identified the following broad CC Agent training goals:

CC training goals

CC training goals B

These training goals translate into the following metacognitive skills that a Call Centre Agent needs to learn and which will be taught through the METALOGUE system:

CC training goals C

To this effect, DialogCONNECTION Ltd and myself are looking for UK-based Call Centres, preferably with multilingual agents, that would like to participate in the course of the project.

 

What we need from you

Ideally, we would get access to real-world Call Centre Agent-Caller/Customer recordings. However, simulated Trainer – Trainee phone calls that are used for situational Agent training are also acceptable (either already available or collected specifically for the project). 2 hours of audio (and video if available) would suffice for the 1st year of the project (needed by October 2014). By the 2nd year (Dec 2015) we would need a total of 15 hours of audio. The audio will be used to train the METALOGUE speech recognisers and the associated acoustic and language models, as well as its metacognitive models. We are looking for Call Centres that are either small and agile (serving multiple small clients) or large (and probably plagued by the well-known agent burn-out syndrome). Strict EU Guidelines for data protection will be applied on all the collected and all the published data (e.g. caller anonymisation, sensitive data redaction) and ultimately YOU determine what can and what cannot be published both during and after the project has ended.

 

What’s in it for you

  • Participation, input in, early access & evaluation of all intermediate pilots as they are developed (No need to wait until the end of the project like the rest of the world!)
  • Provide feedback, express wishes with regards to your own requirements for features and functionality (i.e. the pilots and the end system will be customised to your own needs!)
  • Full METALOGUE system at the end for free, customised to your needs and requirements (no source code, or speech recogniser, just the system as-is)

 

If I have sparked your interest, please get in touch by leaving a comment to this post or contact us through our company website. Here is a handy PDF with the invitation to Call Centres (METALOGUE Poster).

 

You can get updates on the progress of the METALOGUE project by connecting with us on LinkedIn and on Twitter. Watch the future happen now!

 

EU FP7 logo

2013 in review – 4,300 views! :)

12 Jan

The WordPress.com stats helper monkeys prepared a 2013 annual report for this blog.

Here’s an excerpt:

A New York City subway train holds 1,200 people. This blog was viewed about 4,300 times in 2013. If it were a NYC subway train, it would take about 4 trips to carry that many people.

Click here to see the complete report.

Develop your own Android voice app!

26 Dec

Voice application Development for Android

My colleague Michael F. McTear has got a new and very topical book out! Voice Application Development for Android, co-authored with Zoraida Callejas. Apart from a hands-on step-by-step but still condensed guide to voice application development, you get the source code to develop your own Android apps for free!

Get the book here or through Amazon. And have a look at the source code here.

Exciting times ahead for do-it-yourself Android speech app development!

The AVIxD 49 VUI Tips in 45 Minutes !

6 Nov

Image

 

 

The illustrious Association for Voice Interaction Design (AVIxD) organised a Workshop in the context of SpeechTEK in August 2010, whose goal was “to provide VUI designers with as many tips as possible during the session“. Initially the goal was 30 Tips in 45 minutes. But they got overexcited and came up with a whooping 49 Tips in the end! The Session was moderated by Jenni McKienzie, and the panelists were David Attwater, Jon Bloom, Karen Kaushansky, and Julie Underdahl. This list dates back 3 years now, but it’s by no means outdated. This is the most sound advice you will find in designing better voice recognition IVRs and I hated it being buried in a PDF!

So I am audaciously plagiarising and bringing you here: the 49 VUI Tips for Better Voice User Interface Design! Or go and read the .PDF yourselves here:

Image

Image

Image

Image

Image

Image

Image

Image

Image

Image

And finally ….

Image

 

Have you got a VUI Tip you can’t find in this list that you’d like to share? Tell us here!

 

XOWi: The wearable Voice Recognition Personal Assistant

30 Oct

I just found out about the new venture of my colleagues, Ahmed Bouzid and Weiye Ma, and I’m all excited and want to spread the word!

They came up with the idea of a Wearable and hence Ubiquitous Personal Voice Assistant, XOWi (pronounced Zoe). The basic concept is that XOWi is small and unintrusive (you wear it like a badge or pin it somewhere near you) but still connects to your smartphone and through that to all kinds of apps and websites for communicating with people (Facebook, Twitter, Ebay) and controlling data and information (selecting TV channels, switching the aircon on). Moreover, it is completely voice-driven, so it is completely hands- and eyes-free. This means that it won’t distract you (if you’re driving, reading, working) and if you have any vision impairment or disability, you are still completely connected and communicable. So, XOWi truly turns Star Trek into reality! The video below explains the concept:


The type of application context is exemplified by the following diagram.

XOWi architecture

And here is how it works:

Ahmed and Weiye have turned to Kickstarter for crowdfunding. If they manage to get $100,000 by 21st November, XOWi will become a product and I will get one for my birthday in March 2014! :D Join the Innovators and support the next generation in smart communicators!

TEDxSalford 2012: Best of

13 Apr

I can’t believe it’s already been a year since TEDxSalford! TEDxSalford took place on a very sunny Saturday (28th January) at the futuristic Lowry building in Media City, Salford.

I was tweeting for most of the event  and compiled a list of all my relevant tweets and retweets both from the day and in the build-up to the event in this post. Below is the Best of!

TEDxSalford Logo

Tweets – Best of!

Maria Aretoulaki

Jeremy Rifkin: Primitive man’s mind: food, shelter, sex / Modern man’s mind: beer, coffee, apps ! @TEDxSalford http://www.ted.com/talks/jeremy_rifkin_on_the_empathic_civilization.html
30 Jan

Maria Aretoulaki

Amy Purdy: If you were writing a book about your life, how would you like it to go? TEDTalk 3 @TEDxSalford #TEDxSalford http://www.ted.com/talks/amy_purdy_living_beyond_limits.html
In reply to TEDxSalford
30 Jan

Maria Aretoulaki

@herbkim @TEDxSalford was mindblowing! So much intellect, so much empathy, so much emotion, all rolled into one. A blog post is in order!
In reply to Herb Kim
30 Jan

“Nothing is impossible.” -@astro_ron #tedxsalford

Retweeted by Maria Aretoulaki

Maria Aretoulaki

Umut Kose: each of us produces 340 million neutrinos per day that reach the farthest corners of the universe #TEDxSalford
28 Jan

Gemma Cameron ‏ @ruby_gem

“Do you remember your first time with the Internet?” #TEDxSalford
Retweeted by Maria Aretoulaki
28 Jan

Maria Aretoulaki

Tom Hingley (Inspiral Carpets): old bands prob reform in order to make money to buy their sound recordings off the record labels#TEDxSalford
28 Jan

Maria Aretoulaki

Tom Hingley (Inspiral Carpets): that’s what record labels are now – content businesses #TEDxSalford
28 Jan

Maria Aretoulaki 

Tom Hingley (Inspiral Carpets): we’ve moved away from BC and AD to BEFORE INTERNET and AFTER INTERNET #TEDxSalford

28 Jan

Maria Aretoulaki

Tom Hingley (Inspiral Carpets): the current copyright laws are useless #TEDxSalford
28 Jan

TEDxSalford Programme

 

The first time ever someone ordered a pizza with a computer!

23 Jan

In 1974 Donald Sherman, whose speech was limited by a neurological disorder called Moebius Syndrome, used a new-fangled device designed by John Eulenberg to dial up a pizzeria. The first call went to Dominos, which hung up. They were apparently too busy becoming a behemoth. Mercifully, a humane pizzeria – Mr. Mike’s – took the call, and history was made. It all plays out below, and we hope that Mr. Mike’s is still thriving all these years later….” (Smithsonian.com Blog)

Speech synthesis on this computer was rather slow, and it also apparently required “Yes/No” questions to just simply generate a “Yes” or a “No” too. Still, it could also synthesize other phrases, such as the pizza toppings (pepperoni and mushrooms, salami ...), the complex delivery address (the Michigan State Computer Science Department), as well as the contact number for callback. So not bad at all!

I was touched by the patience and kindness of the pizza place employee. He would patiently wait for up to 5 seconds for any answer, which must have been unnerving in itself! And now he is part of History! Good on him!! And well done to the Michigan State University‘s Artificial Language Laboratory and Dr. John Eulenberg!

Follow

Get every new post delivered to your Inbox.

Join 342 other followers