SpeechTEK 2009
SpeechTEK 2009 was August 24-26 at the Marriott Marquis in New York City. For Voxeo, this is one of our largest shows of the year and we had a strong presence at the event. On this page, we provide links to news releases, demos and also a list of sessions in which Voxeons spoke.
For those on Twitter, we were tweeting live using our twitter.com/voxeo account about events, activities and prizes. Please follow us to stay up-to-date.
BOOTH
We were at booth #800 on the left side of the entrance hall into the exhibit area.
NEWS RELEASES
- Voxeo And Nu Echo Announce Plan To Speed Development Of Voice Applications
- Voxeo Announces Prophecy 10: The Unlocked Communications™ Platform
Discussion:
PHOTOS
During the event, we took a number of photos that are available via Flickr at:
DEMOS
We had a number of demonstrations at SpeechTEK 2009. Here are links to available demos:
- SpeechTEK411 Multi-Channel Demo – query the SpeechTEK schedule to find out what is going on via voice, SMS, IM or Twitter.
VIDEO
At the Voxeo booth, Dan York recorded a brief interview with Jose de Castro about the 2,000-port netbook demo and the new VoiceObjects analytics:
Rich Tehrani of TMCnet also recorded and posted a quick interview with Dan York at our booth:
SPEAKERS
Voxeo team members spoke at these sessions:
Monday, August 24, 2009
2:15 p.m – 3:00 p.m, C104 – Voice Interaction Optimization
Optimizing Speech Recognizer Rejection Thresholds
Dr. Daniel C Burnett, Director of Speech Technologies – VoxeoThis session will explain ASR (automatic speech recognizer) confidence rejection thresholds: what they are, where they come from, and their criticality to your ASR-enabled IVR. We describe the steps necessary to optimize this important threshold value throughout your application, covering transcription, the importance of grammar coverage, and an explanation of terms such as the Equal Error Rate. This session is ideal for those ready to take their ASR-enabled IVR tuning to the next level.
SLIDES: Available here: http://www.slideshare.net/voxeo/speechtek-2009-optimizing-speech-recognizer-rejection-thresholds
4:15 p.m – 5:00 p.m, D106 – Security
Securing Cloud Telephony
Dan York, CISSP, Director of Conversations – VoxeoAs voice and self-service applications move increasingly into the cloud and to IP communications, what do you need to be concerned about with regard to the security of hosted solutions? If you grow to trust the cloud, how can you be sure it will be there for you? What protections can you put in place? What backup plans can you establish? What questions should you ask potential hosted/cloud vendors? In this session, security professional Dan York will walk you through the basic risk areas of voice-over-IP security, explain how those relate to both hosted and hybrid configurations and leave you with a concrete list of questions to consider in considering hosted/cloud options.
SLIDES: Available here: http://www.slideshare.net/voxeo/speechtek-2009-securing-cloud-telephony-aug2009
Tuesday, August 25, 2009
8:00 a.m – 8:45 a.m, SD203 – Scripting Languages for Speech Application
MODERATOR: Jose de Castro, Voxeo
ECMAScript, JavaScript, PHP, Python, Ruby, Groovy, and other scripting languages are used to develop speech applicaitions. What are the strength and weaknesses of each scripting language. Exchange insights with other speech application developers about the do’s and don’t’s of scripting languages.
SLIDES: As this was a discussion session, no slides were used.
10:45 a.m. – 12:30 p.m., LAB 3: Mobile Devices
Voxeo Participant: Michael Codini, Managing Director and CTO – Voxeo Germany
This workshop will showcase the latest operating systems and development environments of industry leading handsets. Innovative applications and the SDKs used to build the applications for different handsets will be the primary focus.
New multimodal applications appear on a wide range of phones from low-end devices to smartphones. The speech technology can be embedded with the device or server-based and accessed over a high-speed mobile network thereby providing greater speech processing power while still maintaining thin client benefits yielding longer battery life and low memory requirements.
Device functionality has evolved quickly with such advances as wide screen displays, multi-touch interfaces, accelerometers, sensors, GPS, and integrated iPod functionality. The sophistication of today’s mobile devices has caused a worldwide flurry of new applications that have spawned new ways of communicating, new forms of entertainment, easy access to information, and a variety of location based services. And with open source trends and widely available tools has come a growing community of application developers making devices compelling.
SLIDES: As this was a discussion session, no slides were used.
Wednesday, August 26, 2009
8:00 a.m – 8:45 a.m, SD303 – Taking a SIP of Java-Building Voice Mashups Using SIP Servlets
MODERATOR: R.J. Auburn, Chief Technology Officer – Voxeo
The Java world has seen more than its fair share of telephony APIs come and go over the years. Things like JAIN SIP, JTAPI, Parlay, and JAIN SLEE have been showing up on product road maps for several years now, but SIP Servlets (just released as a 1.1) are finally seeing some industrywide adoption in application servers, both closed and open source. SIP servlets provide a simple API that mimics the widely deployed HTTP servlet model, allowing for Java developers to easily adapt their existing code and framework for communication applications. This session will provide a short introduction to SIP servlets and show people how they can quickly create a converged application using the technology. We will also show how you can quickly plug into simple web APIs using SOAP and REST to create quick web mashups.
SLIDES: As this was a discussion session, no slides were used.
9:00 a.m – 10:00 a.m, KEYNOTE PANEL – SaaS in Speech
MODERATOR: Nancy Jamison – Jamison Consulting
The low-cost, high-value of the Software-as-a-Service (SaaS) model, which has already revolutionized the CRM market, is now making inroads into the speech industry. Hear what some of the leading SaaS speech technology vendors have to say about SaaS in the speech technology industry.
- Paul Watson – Convergys Corporation
- Jamie Bertasi, General Manager of Business Solutions – Tellme, A Microsoft Subsidiary
- R.J. Auburn, Chief Technology Officer – Voxeo
- Dan Reed, Corporate Vice President – Voxify
SLIDES: As this was a discussion session, no slides were used.
11:45 a.m – 12:30 p.m, C302 – Improving Grammars
MODERATOR: Dr. Daniel C Burnett, Director of Speech Technologies – Voxeo
The Art and Science of Speech Grammar Coverage Analysis
Dominique Boucher, Lead Software Developer – Nu Echo Inc.How to Effectively Add Weights to SRGS Grammars
Stephen Keller, Project Manager – LumenVox
SLIDES: As Dan was moderating, he had no slides for his part of the session..
10:45 a.m. – 12:30 p.m., DEMO 2: In Beta: Products in R&D
Voxeo Participant: Jose de Carlo, Senior Software Engineer – Voxeo
Jose will be demonstrating Tropo.com.SpeechTek’s “In Beta” lab will showcase products and services in beta — that is, ones that are not quite ready for full commercial deployment, but ready enough for friendly testing and early adopters. Participating companies will showcase beta products and services with hands-on, individual or small-group demonstrations. Attendees can expect short, informative, and educational discussions about new and interesting products related to speech technology. Some products and services are targeted to speech technology professionals, some to general products and services industries, and others to the public as a whole.
SLIDES: As this was a discussion session, no slides were used.
RSS Feed
