Archive for the ‘Events’ Category

Announcement: Voice Days, Wiesbaden, Germany, Oct. 15-16, 2008

Sunday, August 31st, 2008

See the Voice Days website, as well as my report from the 2007 edition. Note this year’s conference won’t be held in Bonn, but in Wiesbaden.

Announcement: Vocal Expo Paris, Oct. 2nd, 2008

Sunday, August 31st, 2008

See the VocalExpo website.

Announcement: Voice Biometrics Conference London, Nov. 19-20, 2008

Sunday, August 31st, 2008

See the Voice Biometrics website.

Announcement: Voice Biometrics Conference New York, May 14-15, 2008

Friday, April 18th, 2008

See the VoiceBioCon website.

eComm2008, day 3: calling with plants, and other innovative business models

Saturday, March 15th, 2008

The third and last day of the Emerging Communications Conference in Mountain View, CA focused in on innovation.

IBM Think logos at Computer History Museum in Mountain View, CA

Keynote speaker and Chief Analyst Martin Geddes from STL Partners had no trouble convincing the audience that the telco companies need to reinvent themselves as providers of data logistics services. By providing a frictionless platform in-between upstream organizational customers and downstream individual customers, the telcos can source new revenue streams, just like the logistics companies from the freight business have successfully done for decades.

eComm2008 in Mountain View, CA: telcos are sitting on massive amounts of latent data assets

In the Telco 2.0 world, two-sided business models will allow the carriers to exploit the massive amounts of valuable but latent data assets they already own. For example, the airline that brought me to Silicon Valley and back could have offered me a highly personalized 5-day data plan, if only the local telco company had made it dead easy for them to do so. All the information needed to organize the transaction already exists – it’s just waiting to be recombined and exploited.

Data portability is another precondition for a flourishing Telco 2.0 world. Mobile operators could take over from the Web 2.0 social networking sites in this area, as they know their customers better than anyone else thanks to the billing relationship. But it won’t work if management of contact lists, pictures, music files, ringtones and the like are mandatorily coupled with data access.

Nathan Eagle (MIT) turning constraints into innovation in Africa

Abundance of information may actually cloud our view on how to select and recombine the useful bits. A possible antidote and innovation strategy is to go back to basics. This is what Nathan Eagle from MIT is experiencing in his work as facilitator of developmental entrepreneurship in Nairobi, Kenia. The 5-year old phones that the local population are using basically allow them to call and to send text messages. These constraints are a bonus in that they force Nathan Eagle and his team of local students and entrepreneurs to be more innovative. As a result, new forms of communication spring up, like flashing, where consensual meaning is attached to the number of times a phone rings. The advantage: zero cost. Another application uses SMS to vastly improve the supply chain of a blood bank. What better motivation to innovate is there than the opportunity to save lives with 250 lines of code?

Hi, this is your plant calling - David Troy at eComm2008 in Mountain View, CA

Of course, not every innovation grows out of a pressing in-your-face user need. Some Silicon Valley innovators, e.g. Ebay’s Pierre Omidyar, have become entrepreneurs and even billionnaires by accident. At the outset, there needs to be a desire for experimentation and playfulness. This is mostly a matter of personal or organizational mindset and culture. Not just knowledge, but also – if not mostly- imagination.

Dave Troy is certainly a case in point. He’s the creator of the mashups twittervisionflickrvision, and spinvision. He also makes thirsty plants call up their negligent bosses, facilitates political campaigns and steers robot vacuum cleaners by phone. Not every innovation like this is monetizable, of course, but that’s OK. What enables this kind of emergent innovation is the availability of open networks, open content, open devices and open source code. And an open mind, I should add.

Brian Capouch preserving historic houses with technology - eComm2008 in Mountain View, CA

Personal drive and attitude indeed make a big difference. Brian Capouch, a computer science professor who lives in rural Indiana, applies Asterisk and other open source technology to preserve historical farmland houses from vandalism and destruction. He also runs a wireless farm network for his local community. It’s a tough job, but someone’s gotta do it!

Bridging the communication gap between Web and telco worlds

Shirish Andhare from Sylantro presented a human resources methodology to help bridge the culture gap between the Web 2.0 and the incumbent telco world. As said in yesterday’s post, the two worlds are doomed to collaborate in order to grow the pie. New multiplay service models need to see the daylight, with voice being only a component in a broader high-value solution. Elaborating on this last topic, Trevor Baca from Jaduka presented 10 usage contexts in which voice plays an important role. I mostly retain the following tags: urgency, emotion, place (to a minor extent: time), people, and, last but not least: enterprise. On a related note, Benoit Schillings from Trolltech stated that the best strategy to have users accept new features or concepts is to piggyback on what they already know and can relate to. In other words: innovative application features need to be positioned in the user’s mind.

It is an impossible task to summarize the learnings from 3 overstuffed days into a few lines. But let’s try anyhow:

  • Telco/Mobile 2.0 is not equal to squeezing Web 2.0 principles into the existing telco environment
  • It rather requires a radical rethink of existing technologies, organizational structures, work culture, service & product offerings, and, above all, business models
  • Innovation is an outside-in process; organizations need to open their windows and let the fresh air flow in. The answer is blowing in the wind
  • Technology is used by humans. Humans have social and professional relationships. Technology that facilitates these relationships wins
  • End users always have the last word: they will vote with their clicks

eComm2008, day 2: Tangoing with the telcos

Friday, March 14th, 2008

On day two of the Emerging Communications Conference 2008, multiple speakers focused on the topic of (lack of) openness, in its various forms.

Google’s Group Manager of Mobile Platforms Rich Miner explained Android’s goal of taking away constraints that hamper innovation across the mobile application stack. To bridge the gap between low-level hardware capabilities and ease of use, we need to overcome more than human-factor limitations like small screens and keyboards – these problems can be solved by design, as the iPhone proves. Compelling applications are useless if they’re not easy to discover, distribute, and install. And they won’t be built in the first place unless frictionless business models are in place to stimulate and reward the developer community. So value-killing gatekeepers in the telco or software organizations must get out of the way.

Rich Miner, Google Android Project Manager at eComm 2008 in Mountain View, CA

Android sceptic Dean Bubley pointed out that the large majority of smart phone users don’t care about software stacks and extension capabilities. All they want is a pink phone with a camera and a good battery that will play music and videos. They’re not waiting for mobile Internet applications that come with installation procedures, user logins and extra costs. The $100 billion SMS market will be difficult to substitute overnight.

Apart from the telcos’ cash cow concerns, there’s also an issue of brand protection. It should come as no surprise that Apple is maintaining a firm grip on what applications can make it to the iPhone Apps Store, even though the SDK is free and the Standard code signing process only costs a symbolic  $99. Christopher Allen, who recently organized the first iPhoneWebDev camp, gave a long list of constraints that Apple still imposes on the iPhone developer community. What it comes down to is that in the end, Apple can prohibit anything. So the barriers may be lowered – that’s great – but they’re far from gone.

Crick Waters from Ribbit at eComm2008 in Mountain View, CA

Whereas the Apple iPhone enables innovation on the mobile device, Silicon Valley startup Ribbit goes way beyond this old model we all know so well. Co-founder Crick Waters likes to describe his company as Silicon Valley’s First Phone Company. Whereas the iPhone and its siblings function as a very smart presentation layer on top of a generic mobile Internet, Ribbit takes a radically different approach: it offers a complete platform that places itself in the middle of the cloud, in between the telco networks and the Internet. This unique position allows for much deeper integration and enables a complete redefinition of deeply rooted concepts, like – to name one thing – a phone call.

Ribbit has the appearances of a Web-based CTI platform, but at the scale of the Internet, and is completely open. Despite its disruptive and potentially threatening position, Ribbit partners with incumbent telcos in a revenue-sharing business model. About 3500 Flex developers have already signed up for Ribbit’s developer program, and the first Consumer and Enterprise showcases are available. For the moment, the service is only connected to US carriers, but in these times of blurring geographical phone boundaries, that should not be a problem. To be watched closely!

If companies like Ribbit push incumbent telco companies out of their central position towards the edge of the ecosystem, maybe it’s time these carriers start reevaluating their assets to see what’s left for them in this new world – apart from selling cheap minutes and sending text messages. As Kousjik Chatterjee from Embarq and Johannes Ernst from NetMesh pointed out, one asset that the carriers should cherish is their billing relationship with millions of customers. Billing implies authentication and identity, so here’s an opportunity not to be missed. Link telco customer identity with OpenID and voice biometrics, and we have a new phone-based service for accessing the Internet.

The openID adoption curve presented at eComm2008

What do we need country-specific phone prefixes for, other than as an excuse for carriers to overcharge for international connections? If we want phone numbers to be long-life identifiers for the people that use them, number portability must be able to travel across country borders. CEO Rod Ullens from Brussels-based VoxBone announced that the ITU has granted his company the right to create and distribute a new range of country-neutral numbers with prefix 833. VoxBone will offer the worldwide numbers to the carriers at no charge, hoping that they will pas them on to their customers at the same price. The incumbents would share revenue with VoxBone for all calls originating from the PSTN, and a second revenue stream will come from global premium services. The business model challenge will be to make sure that the end user will not suffer from exorbitant transfer costs. Otherwise the iNum initiative will die a rapid death.

VoxBone CEO Rodrigue Ullens announcing the iNum initiative at eComm2008

Another remarkable initiative was presented by Terranet’s Founder & CEO Anders Carlius. His company has identified an unserved audience in the Third and Fourth Worlds that do not deserve to be overlooked, if only for the yearly revenue potential that they represent: $240 billion! Terranet’s approach is to distribute cheap peer-to-peer mesh phones in local communities, which would cater for daily needs like security & emergency, or simply calling home. As a bonus, the technology enables a great leap forward in crossing the digital divide. It should come as no surprise then that Terranet is bombarded with interest by governmental and private organizations, especially after this BBC interview.

Anders Carlius from Terranet at eComm2008 in Mountain View, CA

On the application side, I first want to mention Fonolo, a “deep calling” service based on reverse-engineered IVR applications. I’m a bit sceptical about the operational scalability of the system, and, frankly, also about the solution that this service offers. It’s already bad enough that IVR menus are not always as user-friendly as they should be; starting a desktop and opening another web application is not the answer. Moreover, just like the GetHuman initiative, it might actually serve as an excuse for IVR and speech application builders not to invest in usability. Which would be kind of counter-productive.

The second service that caught my attention is, for its simplicity, quality and rapid adoption.

DialDirections service presented at eComm2008

Conclusion: day two of eComm2008 was stuffed with presentations and ideas that can and occasionally will change the world. On the one hand, the innovators at the edge take their distance from the carriers or, like Ribbit, push them out of their luxurious central position; on the other hand, the incumbents’ weight is so large that one way or another they cannot be fully ignored or circumvented. This tango has only just begun, and every now and then the dance partners will inevitably step on each other’s toes. But as everyone knows: it takes two to tango.

eComm2008, day 1: Hear the voice of disruption

Thursday, March 13th, 2008

I’m in Mountain View, California for the Emerging Communications Conference, where 300 – almost exclusively male – people have gathered to discuss the next innovation waves in telco land. Like many innovations, this conference itself is born out of frustration. Frustration with US telcos concentrating on selling cheap minutes. Frustration with European mobile operators asking ridiculous prices for simple call termination. Frustration with a VoIP revolution that has taken place but in a sense has just as well gone unnoticed by the public at large – who couldn’t care less about technology. Vested interests – in 3G investments, for one thing – and organizational inertia have indeed created a classic innovator’s dilemma for the large carriers, that stifles innovation. Creating the conditions to get out of this situation is the main topic of eComm2008.

Emerging Communications Conference 2008 in Mountain View, CA

The first condition for a blossoming communications market lies in a distribution of power. Today, the big players and their lobbying arms in Washington DC or Brussels still hold the power, but an inevitable grassroots countermovement is developing. Speakers like Jonathan Christensen from Skype and network neutrality activist David Isenberg pleaded for a natural segmentation of competences in the market. In this setup, carriers should do what they do best: carry voice and data through their pipes, and even provide some billing services – for those who need it. At the edge of the network, business and application developers – who are supposed to know what end users like and dislike – then make user-centric innovation go forward. That’s the idealistic scenario. The one trillion dollar question is how to make this happen. The answers put forward on day one of the conference evolved around the value of simplicity, a redefinition of voice, and the importance of trust & identity.

David Isenberg using Martin Geddes as presentation device at eComm2008 in Mountain View, CA

The value of simplicity was epitomized by Twitter. Lead architect Blaine Cook – a sociologist by education! – ascribed Twitter’s phenomenal success by the fact that all complexity in the system is hidden from the end user – all they can send and receive are 140 character messages. But building addictive systems that are simple to use is not for the faint-hearted. Without going into much detail, Blaine Cook acknowledged that Twitter has had issues in scaling up that are more than mere growing pains. Using XMPP as an alternative for SMS may alleviate problems in a structural way, but Peter Saint-André pointed out that the main challenge for mass adoption of presence in a mobile setting is … battery power.

Twitter's Blaine Cook at eComm2008: simple systems are complicated to build

On the voice front, technologists Ken Rehor from the VoiceXML Forum and Voxeo CTO RJ Auburn presented architectural updates from the VoiceXML world. Useful to know if you’re not a specialist, but not ground-breaking by themselves. Their presentations go to show that the availability of standardized (VoiceXML or other) platforms may be a necessary, but certainly not a sufficient condition for innovation. Thomas Howe from the eponymous company asked the more important question of how commoditized voice can get a value boost. The answer lies in the application context: for a package transportation company, a failed call may mean a failed delivery – and that’s a real cost. In other contexts like voice cards – my example – the value is more of an emotional nature. Thomas Howe’s main message is this: don’t build voice applications, but augment existing applications and business processes with voice, where useful.

Thomas Howe looking for value in voice at eComm2008

Another fundamental issue in the Internet & telco industry is trust & identity. Piotr Cofta, Chief Researcher at BT, sees trust & identity as necessary communication shortcuts without which society would not work. To drive societal innovations he envisions a layered stack of responsibilities in which trust and identity play the same role as the transport and network layers in the Internet’s well-known OSI model. Contrary to its counterparts in the US, British Telecom had made an important first step in opening up its network through its 21st Century Network, 21CN in short. There is no need for more, but for better communication.

eComm2008: trust and identity

My conclusion for day one: if you don’t innovate, your competitors will. Or worse: a new industry will. We have to be careful not to inflate the meaning of disruptive innovation – buzzword bingo always lurks around the corner. But telco execs beware! A change is gonna come … whether you like it or not.

Announcement: Emerging Communications Conference in Mountain View, California, March 12-14, 2008

Tuesday, February 26th, 2008

I just made my reservation for eComm2008 which takes place on March 12-14 in the Computer History Museum in Silicon Valley, California.

From the website: “eComm is a brand new telecom event for those interested in radical innovation and seizing the next opportunity wave.”

Yeehaa! Or, as a former Belgian prime minister would say: let the beast go!

If you’re interested in meeting me there, let me know.

Speech Technology Seminar in Brussels issues call for further professionalization

Monday, February 25th, 2008

On the 12th of February the Belgian speech technology industry gathered in the Belgacom Towers for the second edition of the seminar “Speech Technology: Customer Experiences in Belgium”. Apart from seminar host Belgacom, the event was also sponsored by Acapela, DBScape, Genesys, NextiraOne, Nuance, Quentris and The Ring Ring Company. Chairman Alain Rondenbosch of the organizing Speech Technology Workgroup was very pleased to welcome a larger audience than at the first edition in November 2006.

Chairman Alain Rondenbosch of the Speech Technology Workgroup welcomes the audience at the second Speech Technology Seminar in Brussels, Belgium

The format of the seminar is simple: give the floor to the actual end users of speech technology – mainly call centre managers in our setting – rather than to the vendors. As a novelty, Voice User Interface (VUI) design expert Tom Houwing, director of VoiceAndVision, was invited this year as keynote speaker and moderator.

Keynote speaker and moderator Tom Houwing evangelizing professional Voice User Interface design at the Second Speech Technology Seminar in Brussels, Belgium

In the first part of his keynote address, Tom Houwing sketched a painful but – sadly enough -  realistic picture of how otherwise professionally run call centers give the automated voice channel the proverbial stepmother treatment. Everyone knows how to speak and listen, right? Not! Causes of voice user interface neglect by automation project champions are naivety, ignorance, or downright complacency. These are my own terms, not Tom Houwing’s, but I’m sure he would agree. Mr. Houwing gave the example of a large utility company who failed to apply even the simplest of user interface design principles to its main customer service line: offer the most frequently chosen option in first, instead of in sixth place.

On a positive note, I must mention Tom Houwing’s wonderful account of a stepwise disambiguation strategy for the speech recognition of loosely structured alphanumeric license plates: the uncertainty implicit in the N-best result list is personified by a dumb subordinate who doesn’t know how to jot down license plate numbers; he is consequently yelled at by his condescending, bossy boss, who himself is interfacing with the caller – in a more charming tone. This is one brilliant example of how an inherent challenge of speech recognition is not just being overcome, but turned into a funny customer experience that also works, in all meanings of the word.

As could be hoped or feared, the end user presentations that followed would give the keynote speaker and the attentive audience more than enough inspiration on do’s and don’ts in VUI and customer interaction design.

Catherine De Baets, Marketing Manager of the Belgacom Call Centre, speaking at the second Speech Technology Seminar in Brussels, Belgium

Marketing Manager Catherine De Baets of the Belgacom Call Center explained how a legacy static script-based IVR was transformed into a fully dynamic version. The business goal was to speed up reactivity through maximum agility on the rapidly changing market in the sales, marketing and complaint handling domains. By relying on a centralized, cross-channel Customer Relationship Management (CRM) database, all IVR menus at Belgacom Call Center are now data-driven. This way, customers who are not eligible to a certain service (e.g. Belgacom TV) now do not get this option on offer anymore – and that is certainly a bonus. Even more important is the flexibility gained by Belgacom’s internal business users, who don’t rely on the IT department anymore to deploy their marketing initiatives. As a consequence, the time to market of a new promotion or other marketing action has dropped to between 4 hours and 2 weeks.

Although, according to the speaker, the profile-based approach has enhanced customer satisfaction, the question must be asked if the exclusive reliance on text-to-speech – identified from the start as a key success factor, by the way – is really necessary. It is a common misconception to believe that because text-to-speech is particularly apt at reproducing dynamic text, all dynamic text necessarily needs to be reproduced by text-to-speech. The real decision criterion should be whether the structure of the text itself is predictable or not. Judgeing from a test call I made after the seminar, the IVR menus are indeed dynamic, but their structure is not. As a result, the auditive quality of the overwhelming majority of menu items could be greatly enhanced by prerecording and postproducing them once and for all, with enough variation for good prosody. Audio file concatenation would then take care of the rest. This would, as an example, prevent phone numbers from still being read aloud one digit at a time, which is not customer friendly at all, let alone state of the art.

Jean-Michel Motte, System & Network Manager BeTV addressing the audience at the second Speech Technology Seminar in Brussels, Belgium

Contrary to the kind of on-the-fly text-to-speech discussed above, BeTV’s System & Network Manager Jean-Michel Motte presented a use case of the same technology in the less dynamic setting of a movie ordering service by phone. Not to mention a name, Acapela’s Virtual Speaker was showcased as an off-line technology situated half-way between dynamic text-to-speech and prerecorded, concatenated prompts. The tool allows off-line prompt creation and enhancement, but without the need for a studio. Or a speaker, for that matter, but do note you can roll your own TTS voice these days. Interestingly enough, Mr. Motte showed how the correct pronunciation of foreign names like his own company’s name could be forced by misspelling it, rather than by creating an entry in the pronunciation lexicon. For sure a pragmatic use of speech technology!

Valérie Nève, Call Center Manager Leroy Merlin, speaking at the second Speech Technology Seminar in Brussels, Belgium

Valérie Nève, Call Center Manager at Leroy Merlin in Lille (Northern France, close to the Belgian border) presented a call center routing and CRM integration case based on Genesys, Vocabase and Acapela technology on the IVR side, with NextiraOne France as integrator. In 2007, the company’s 25 expert advisors treated 107.000 incoming phone calls. A major objective of the automation project was to bring down the abandonment rate from 30 to 5 percent. As each contact represents a revenue opportunity, losing one call out of three is clearly unacceptable. Through DTMF menus, customers now select the competence level required to answer their question, and get transferred to the right agent. In case no agent is available, the CRM system immediately proposes a call-back time frame. The IVR line also gives access to other personalized services like loyalty card information, credit services, and order taking.

At this stage the Leroy Merlin project focus seems to have been more on back-end CRM integration than on front-end speech automation – speech recognition is indeed still on the to do list. Like the Banksys case presented at the previous seminar, speech technology often only comes into play after the necessary back-end processes have been put into place. In a way, this is good, because it reduces project complexity and prevents speech technology or classic IVR front-ends from getting blamed for failing back-end processes. This being said, there’s not much point either in creating wonderful back-end solutions if they can’t be reached because of an overly complex IVR menu structure. As far as I can recall, the presentation did not mention any hard figures on customer satisfaction. In any case, my advice to Leroy Merlin would be to benchmark the current DTMF-only interface, have a VUI expert – not an engineer! – design the speech interface, implement it, and measure customer satisfaction and other relevant business key performance indicators again.

Guido Vermeire, Project & Technical Support Manager Belgacom, speaking at the second Speech Technology Seminar in Brussels, Belgium

After the break, we got news from Lisa, Belgacom’s fully automated directory assistance, reachable in Belgium at 1234. The last time I heard from her was almost three years ago at Voice World 2005 in London. When the service was launched in October 2004, it failed to live up to the high expectations raised by the publicity campaign; that some journalists openly tried – and still try – to ridicule the system did not help its reputation either. A bit cheap, because it would not be difficult either to “prove” that DTMF recognition doesn’t work if you decide to wear boxer’s gloves. Anyway, whether we like it or not, many people inside and outside the industry still perceive and refer to Lisa as their personal benchmark of state-of-the-art speech technology in Belgium. So any news from Lisa is important news.

To put everything into perspective, Guido Vermeire, Projects & Technical Support Manager at Belgacom Directory Information Services started his exposé with some figures from the human-manned DA numbers 1207 (Dutch), 1307 (French), 1407 (German) and 1405 (English). In 2006, about 480 call center FTEs handled a bit less than 42 million DA inquiries, that’s 3.4 million a month, 115 thousand a day, or 240 per FTE per day. In 2005, Lisa/1234 handled 33 thousand calls a month – a mere 1% of all DA inquiries. The goal of 83% of these automated inquiries was to find the phone number of a residential or business listing; the remaining 17% were reverse queries, starting from a known phone number. For 2006 and 2007, no figures were made available. In 2008, the monthly call volume of Lisa/1234 has risen to 46 thousand – still negligible compared to the non-automated case – but the breakdown by call type has completely changed: only 29% of normal business or residential queries, versus 71% of reverse ones.

I could not prevent a deep frown when hearing these numbers. But there was more disturbing news. Of 100 normal inquiries handled by Lisa, only 29% lead to a fully automated result. In 39% of the cases, Lisa decides to transfer the caller to a human colleague. That is, if the caller hasn’t asked for such a transfer in the first place, which happens in another 22% of the cases. The remaining 12% cover the premature hang-ups. In reverse search, success and automation rate are around 85%, which is understandable as the automation task only involves recognition of a phone number, which can be done via DTMF.

All in all, this means that Lisa automates around 3900 normal business or residential inquiries a month. That’s 130 calls a day, or half an FTE.

Mr. Vermeire should be admired for his openness and honesty in sharing the list of technical and voice user interface challenges that the Lisa project had to overcome. It was not the list itself that surprised me, but the lack of answer that apparently had been given to address the various problem areas. For example, the “spoke too late” or “spoke too soon” effect needs to be tackled by good prompt design and timeout settings in any speech recognition project. Stopwords and garbage models have been inserted in speech recognition grammars for over a decade. If disambiguation by street name is not an ideal solution, then maybe the solution needs an update. If the dialog is described as “customer friendly but directed”, some serious misconceptions have taken root about good VUI design. And if customers are afraid to be transferred to an operator because it will cost them money – why not take away their fear with a simple prompt? In short: if the water tap is leaking, why not repair it?

The simple but disconcerting answer may be that there has never been a clear and integrated strategy behind the initial decision to develop and launch Lisa. Was there a need for cost reduction in the call center? Probably not, the unions more than likely would have disagreed. Do callers spend too much time in the waiting queue on the human-manned DA line before being served? We don’t know for sure. Was the money spent on marketing a new 1234 number in line with the expected quality of the service running behind it? I’m afraid not. Were the key business and technical performance indicators clearly stated from the start? If they were, they were not presented at the seminar.

I do apologize for all this frankness, but Belgium deserves a better automated DA service than Lisa is able to provide today. If Belgacom won’t or can’t do it, maybe someone else will. Time will tell.

Hans Van Hauteghem, Manager of Product Development at the Royal Meteorological Institute of Belgium, speaking at the second Speech Technology Seminar in Brussels, Belgium

Last speaker of the day was Hans Van Hauteghem, Manager of Product Development at the Royal Meteorological Institute of Belgium. He was assisted on the linguistic side by your servant. Together with its partner The Ring Ring Company, the RMI has been offering weather information services by phone for more than 10 years, using prerecorded messages at the start. In October 2006, they switched to a text-to-speech only solution, thereby addressing concerns about consistent message quality, and improving the speed of the service. Weather reports are now updated 5 times a day across all media channels, and made available to the general public and specialized target customers alike. Simple and highly structured data types like sea tides, ephemerides, and UV radiation are coded in XML and only transformed into text later on by a text generation module residing on the IVR provider’s side. More complex, less structured data like the full weather forecasts are manually written by the RMI meteorologists before they cross the wire to the TTS platform.

The solution is not exactly what you’d call rocket science, but it works fine. Indeed, the value of a speech application is not necessarily linked to the amount of technical sophistication that the average IT engineer would like to throw at it. Small and simple can be beautiful! The 160 thousand callers who use the fully automated weather line on a yearly basis surely seem to agree.

In his closing words, Tom Houwing sent a tactful but strong message to the audience that the speech technology world doesn’t stop at the Belgian border. Numerous successful, state-of-the-art and fun speech technology applications are being showcased every year at Voice Days in Germany or SpeechTek in New York.

To conclude in my own words: if the Belgian market is somewhat struggling, this has more to do with a lack of vision, ambition and belief from the large players, than with innate peculiarities of speech technology implementation practices in Belgium as such. If we need to learn one lesson, it’s that successful speech applications don’t depend on speech technology in the first place, but on human factors.

And now, back to work!

Announcement: Plugg conference, Brussels, 19th March, 2008

Tuesday, February 19th, 2008

From the Plugg website: “Plugg is a one day conference focused on raising global awareness for European start-ups in the Web / Mobile 2.0 field.”

I’ll be there.