Technical Development Track
How to Save Money on Your Speech-Enabled Solutions by Being a Smart Customer
Tuesday, November 30 * 9:45-10:30 am
This session is all about being a smart customer. When sourcing a speech enabled solution, whether from a solution provider or via an in-house development team, a huge amount of money and effort can be saved by asking the right questions at the beginning of the process. Far better to think about them at the start, than when it becomes too late to change the foundations on which the solution is built. This session will investigate the key components of speech-enabled solutions and come up with the valuable questions that anyone with an eye on budgets and timescales should be asking.
Usability Surveys to Test Speech Applications
Tuesday, November 30 * 10:45-11:30 am
Usability testing is an evaluation of a customer touch point from a user experience perspective. This session will compare many ways to test usability of speech applications and will show the benefits of the usability survey approach. This process involves thoroughly evaluating usability with several hundred unbiased panelists before deployment to reveal and fix problems large or small. Information will be presented on how usability surveys can provide valuable diagnostic information on voice recognition performance, and on user opinions of overall task completion and satisfaction, voice recognition, call flow options and voice prompt quality. The author will demonstrate how this information can lead to clear improvements to prompts, call flow and recognition performance.
New Economics of Speech in the Enterprise: Driving Down Operating Costs and Increasing ROI
Tuesday, November 30 * 11:45 am-12:30 pm
Call centers today are looking for ways to automate, streamline and improve their customer care programs through voice-enabled technology. Given the ubiquity of the phone, 92 percent of today's repetitive service transactions are directed to call centers. Hiring customer service representatives (CSRs) to handle basic and repetitive requests is expensive and inefficient for many customer programs. While touch-tone systems do overcome some of the inherent agent issues, these systems are still inflexible and unnatural, have menu limitations, are limited in functionality and leave most customers frustrated and unwilling to complete their calls. Today, speech recognition technology offers a more compelling solution for customer self-service and business ROI. Speech has been proven to efficiently handle both basic and complex transactions at lower costs and higher customer service levels.
Avoiding the Pitfalls of Speech Application Rollouts Through Testing and Product Management
Tuesday, November 30 * 1:30-2:30 pm
Speech self-service applications can truly become the "voice of a company." Unfortunately, it only takes one bad experience for a customer to stop using self-service applications. As a result, application performance can have a significant effect on customer loyalty and a company's image and bottom line.
Voice Middleware: A Strategic Component for Future Voice Success
Tuesday, November 30 * 2:45-3:30 pm
A recent quote of Datamonitor, backed up by its recent "Voice Business Value Chain II" voice business report, stated, "Voice applications will increasingly consist of reusable components and modules. In tandem with this trend, voice middleware will grow in prominence and facilitate the development and spread of voice applications, just as today's Web application servers enabled the broad use of Web applications" (Katherine Lam, Technology Analyst, Datamonitor). The emergence of reusable components, templates and packaged applications creates a natural market for toolkits and specialized voice middleware that will aid in development, integration and performance-testing activities. In particular, the tools market will be strong due to demand from small and medium-sized enterprises for which voice solutions (in the form of packages and modules) have only recently become affordable. In spite of this growing demand for tools and managed environments, the Optimizing IVR/Speech Using Customer Behavior Intelligence.
Application Design: Error Handling
Wednesday, December 1 * 8:30-9:30 am
While application designers and recognition experts rightly measure the success of applications by such parameters as "Did the user accomplish his or her task?" and "How accurate is the recognition?," designers must also consider how much the user enjoys using the system. It appears that this does not, however, correlate directly with how accurate the recognition is, but rather, how easy it is to use the system and how elegantly the system handles errors. As much as we wish it were, speech recognition is not perfect. The user often will not perceive whether an error is caused by something he or she did incorrectly, the environment or the recognition engine. Because of this, the system will not always behave the way the user thinks it should. Keeping in mind branding and persona issues, this presentation will offer tips and real-life, case-study examples on handling different types of user and application errors that, if used correctly, create a more robust, helpful voice application that allow users to feel as if the system is working with them instead of against them, and will ultimately leave the user with a good impression of your company's customer service. Dialog and programming tips for error handling include navigation, no matches, no inputs and multiple fields of information filled with one utterance. The session will also address the highly debated topic "Do we apologize for making errors?"
Developing Speech Dialogs--A Designer's Perspective
Wednesday, December 1 * 1:15-2:00 pm
Changing technology allows for the development of innovative ways to build new man-machine interfaces. In particular, adding speech to the mix opens up a host of new possibilities. However, the fast-changing technologies also create a lot of confusion with respect to where and how speech can be applied and what technologies and tools are needed to build effective applications. This presentation will attempt to answer some of these questions from an application development perspective.
Technical Aspects of Deploying a Hosted Speech Solution
Wednesday, December 1 * 2:15-3:00 pm
When deploying a hosted speech solution, VoiceXML developers need to keep several tips and tricks in mind. In this talk, we'll focus on how to get started, what to do during development and what steps to take after deployment. Content will include how to set up the development environment, including choosing VoiceXML development tools, dynamic programming language and an application server. Once set up, developers will learn how to record professional prompts, debug application functionality and measure application success/task completion rates. Finally, we'll review how to improve performance after deployment, including caching and application server tuning.
Architecture of the Speech-Enabled Web
Wednesday, December 1 * 3:15-4:00 pm
The Web is a global information space of interrelated resources. Central to the architecture of the Web are the orthogonal principles of identification, interaction and representation. Identification refers to the URI mechanism by which resources are identified in this information space. Interaction refers to protocols that define the syntax and semantics of messages exchanged by agents over a network (e.g., HTTP). Finally, representation refers to the formats for which data are encoded (e.g., HTML). The modern speech-enabled Web exploits the underlying orthogonality within the architecture of the Web by allowing new representation and interactions formats and protocols to be developed independent of each other. The World Wide Web Consortium (W3C) is active in defining new representation formats for the speech-enabled Web, including VoiceXML, SRGS, SSML, SISR and CCXML. The Internet Engineering Task Force (IETF) is active in defining new interaction protocols that are powering the new speech-enabled Web, including MRCP and SIP. This presentation will help attendees understand the basic ideas behind the latest technologies powering the speech-enabled Web. We'll discuss the "bigger picture" of how, why and where different specifications and technologies are being developed. The major concepts behind each specification will be introduced briefly before discussing how these different technologies interoperate, resulting in exceptionally powerful speech solutions.
Developing Voice IVR Applications Using Host Processing
Wednesday, December 1 * 4:15-5:00 pm
Most of us have heard the term "host media processing" used as a possible alternative to DSPs; but have all developers of voice IVR established what this technological shift could mean for them? This session is intended to share some of the key decision-making points, technical considerations and business benefits that are in the melting pot when looking at this new alternative. A structured review of features, development environments and deployment scenarios will help delegates identify the main points that will lead to a host media processing selection, rather than DSP hardware. Reference will be made to practical learning points gleaned from working with early adopter customers of host media processing technology.
Call Center Applications Track
Sorting Through the Standards: A Primer
Tuesday, November 30 * 9:45-10:30 am
Trying to keep up with the continually evolving speech standards lately seems as murky and unpleasant as wading through alphabet soup. If you're having a hard time keeping your EMMA straight with your SALT and your X + V, we have just the session for you. We'll overview today's standards, explain where they came from, what they're used for and where they're headed. You'll leave this session wondering how you ever got along without it!
How "Natural" Should a Voice...