Archive for October, 2008

VoiceDays 2008 – VoiceObjects-related presentations

Monday, October 27th, 2008

Last week VoiceDays 2008 – the leading German speech technology event – took place. From the VoiceObjects perspective we are looking back to a really successful event. Numerous discussions indicate the growing demand for application development environments that provide independence of underlying IVR technology, that can handle multiple phone channels and modalities, and that provide powerful analytics.

During these two days participants of congress and tradeshow could attend numerous presentations; I want to share the VoiceObjects-related (primary German) presentations with you.

Three presentations were given by VoiceObjects customers, providing good insight into their experience with application development and deployment of automated self-services:

Daniel Hendling, T-Mobile International: Die integrierte Voice & Mobile Self-Service Strategie bei T-Mobile International

Marion Libossek, Telefónica o2 Germany: Der steinige Weg zum sexy Voice Portal

Christian Rosenberger, Swisscom: Das Swisscom-Sprachportal


My colleagues gave two presentations on multi-channel self-services:

Michael Codini, VoiceObjects: Die neue mobile Generation – Selfservice-Anforderungen in der Multichannel Kommunikation

Dr. Andreas Volmer, Multi-Channel Phone Services With VoiceObjects Server


And finally, I gave a presentation on analytics during the Demo-Forum session:

Michael Gill, Analyse- und Tuning-Tools: VoiceObjects Analyzer

D+S europe AG wins VoiceAward 2008

Wednesday, October 22nd, 2008

Just a quick note on a successful phone service deployed on VoiceObjects technology:
D+S europe AG has won the „Best Value-Added Service“ category of the VoiceAward 2008. The VoiceAward recognizes the wake-up service (Weckdienst) as best speech-enabled public phone service.

Award winners were selected by a panel of expert judges attending the recent VoiceDays conference (the German SpeechTek) in Wiesbaden. Judges looked not only for service usability, but also for the short development time and the cost-efficient realization.

The service can be accessed through the German service number 11864 (Deutsche Telekom) or 0900-500 11 55 (premium rate).

Check out the update…

Tuesday, October 21st, 2008

Dear VoiceObjects developers,

We recently updated the Developer Portal with some new product updates. Check out the update below:

  • Now available: VoiceObjects Media Mixer Developer Edition
    VoiceObjects Media Mixer is now available as free Developer Edition. VoiceObjects Media Mixer enables the delivery of innovative video solutions via the creation and dynamic generation of video applications for 3G phones. This optional component to the VoiceObjects Server mixes multiple content types — such as text, images, HTML, audio and video files — and generates video clips in 3gp or Flash video (flv) format.
    http://developers.voiceobjects.com/support-training/media-mixer/


  • New version of VoiceObjects Developer Edition
    Version 7.3 R2 is now available for download, providing a newly designed Test Monitor, an enhanced Storyboard Manager, and several minor enhancements and bug fixes. Users of previous versions of the Developer Edition may use the “Check for Update” from the Developer Edition’s VoiceObjects menu to check for the latest version and to access the provided update package.
    http://developers.voiceobjects.com/downloads/deveditiondownload/


  • Prime Telecom
    To learn more about using VoiceObjects for multiple phone channels try the newly available demo application Prime Telecom. Prime Telecom implements a sample self-service portal for a telecommunication company, supporting three phone channels (voice, text, and Web) in three different languages (US-English, UK-English, and German).
    Additional demos and templates will be published soon.
    http://developers.voiceobjects.com/support-training/developer-edition/demos-templates/


Please note also our next Jam Session on “Natural Dialog Management – Adding NLU and Other Advanced Speech Processing Features to Traditional Voice & DTMF Dialogs” on November 5, 2008. Free registration at http://developers.voiceobjects.com/tech-topics/monthly-jam-sessions/

Best regards,

Michael

Correct me if I’m wrong

Tuesday, October 14th, 2008

Ill-designed voice dialogs can get unnecessarily slow and tedious when they try to over-compensate for speech recognition challenges, may they occur or not. This can drive me nuts: They verify each and every input individually instead of first collecting all input and then confirming all of it at once. With 4 items to collect, for instance, this would reduce the input states by 3 (!), let alone the time those three steps would take. Using VoiceObjects Analyzer, you could easily measure that time and understand that that would be time spent in vain, which might actually cost your organisation money spent in vain! But what can you do?

Well, VoiceObjects 7.3 makes it pretty easy to apply concepts like implicit confirmation and thus correction to your dialogs. As this occurs so frequently in everyday voice applications, I thought I’d write a post on this.

So check out the following call flow excerpt:

The Input object Get Credit Card Type asks the initial question: “What is the type of your new credit card?” and accepts responses such as “Visa”, “It’s mastercard”, “I have an Amex card”, etc. The following Input object Get Credit Card Number collects the number only – at first sight, that is. In reality, it does more. It

  1. implicitly confirms the collected card type by prompting the caller with “And what is the number of your Mastercard?” (The speech bubble icon behind the object name – denoting a comment on that object – hints at the additional functionality of this object; hovering over it in VoiceObjects Desktop would show you the developer’s comment as a tool-tip).
  2. allows a correction of the card type in case it was misrecognized.

This behaviour is not visible per se from the flow as VoiceObjects call flows are usually optimized for readability, deliberately omitting certain details. Showing too much of the innards would make it harder to follow what’s happening on the surface. (I have positive experience with this approach. But here’s an idea: to mention the correction capability of this input state, the developer could have called the Input object Get Credit Card Number (or Correct Card Type) instead).

Now imagine the recognizer got it wrong and the caller actually said “AmEx card”. What could be the caller’s reaction to this question? Maybe something like “No I said AmEx!” (Damnit!). The Input object Get Credit Card Number has an additional grammar defined (via a second Grammar item in the Grammar section of the Input object) that matches corrections like this. But how can the grammar instruct the server to accept this as a correction of credit card type, reset the corresponding variable, apologize, and ask again for the number, as in “I’m sorry. So what’s the number of your Amex card?” VoiceObjects 7.3 introduced the notion of grammar-driven application control to accomplish this. (Did you notice that the server even adapts to the caller’s choice of words in this example, by saying “Amex” instead of “American Express”? I guess that would make for another nice post on naturalness…)

The grammar can return instructions for the server via a special slot vogrammarcontrol; instructions such as “change the value of variable CCType” and “re-process object Get Credit Card Number”. In our example, the corresponding grammar snippet could look like this:

By detecting the slot vogrammarcontrol in the speech platform’s request after caller input and parsing the slot value to arrive at the three instructions varCCType=Amex (set variable CCType to “Amex”), gosub=Apology (process the object with ReferenceID “Apology”, which happens to be an Output object), and continuation=return (continue by returning to the current object and re-processing it), the server naturally responds to the caller’s correction with “Sorry for that. So then, what’s the number of your Amex card?”.

This is one of many possible steps towards more natural man-machine interaction. We at VoiceObjects like to call it Natural Dialog Management. Find more details on the feature of grammar-driven application control in the Input object section of the Object Reference, which is part of the VoiceObjects product documentation. I plan to provide some more examples on other Natural Dialog Management features in upcoming posts… Stay tuned!

Welcome to the VoiceObjects Developer Blog!

Monday, October 13th, 2008

Welcome to the VoiceObjects Developer Blog. The VoiceObjects team is very excited about this new communication channel as this will enrich our growing developer community by sharing thoughts and experiences on various topics.

This weblog will focus on best practices for self-service application design, VUI / GUI design, analytics and reporting, and speech grammar development. Also we are going to cover new market and technology trends and how those impact the VoiceObjects product roadmap. Specifically on developments in the W3C standard bodies around VoiceXML. But also on emerging phone self-service channels such as Video, SMS, USSD, Web Chat and Instant Messaging. And finally we want to report about successful project and solution deployments with our SI partners and customers.

Here are the VoiceObjects team members who  will participate as authors in the Developer Blog:

Andreas Volmer – Presales Manager EMEA
Angelika Salmen – Manager VUI Services
Christopher Schick – Program Manager
Martin Mauelshagen – Program Manager
Michael Codini – CTO
Michael Gill – Director Product Management
Stefan Besling – VP Engineering
Tobias Göbel – Senior Presales Consultant
Volker Kraft – Manager Education Services

If you would like to stay  up-to-date  on what we are doing, please do subscribe to our site’s feed – and please do pass along your comments.  We’d love to hear from you.

The VoiceObjects team