This talk, using real-world examples, examines the common pitfalls of translating application prompts. Strategies for successful translation into multiple languages and cultures are presented, such as creation and maintenance of the integrity of source text, consideration of cultural elements of both source and target language, selecting the best-qualified translator, why a single translator is preferred, how and when to use reverse translations, a glossary of company/industry terms for use by the translator, and concatenation of sentence fragments.

The localization of speech recognition for large-scale spoken dialogue systems can be a tremendous exercise. Usually, grammars are translated by a language expert, and new data is collected, transcribed, and annotated for statistical utterance classifiers — resulting in a time-consuming and expensive undertaking. Typically, though, a vast number of transcribed and annotated utterances exist for the source language. This talk proposes to translate such data via machine translation and use them along with their associated (original) annotations to train statistical grammars.

This session explores the results of a usability test focused on making payments in a speech application. The testing methodology, goals, results, and
findings are presented. Both new and seasoned designers can benefit from this session, which provides useful and surprising data for anyone who has
designed payment features in an IVR.

In recent years, Wizard of Oz (WOZ) testing has fallen out of favor, yielding to full-blown usability testing of coded applications. At the same time, cost-conscious IVR teams have increasingly taken their chances and skipped usability, despite the risk. Perhaps it’s time to resurrect the Wizard, warts and all! This session covers the advantages and disadvantages of WOZ, as well as practical advice on conducting contemporary WOZ tests successfully and inexpensively.

The position of voice portal specialist is the champion for the caller and serves as a liaison between the business and technical units, spanning various departments. This case study follows Blue Shield of California’s journey in IVR design and development during the past 5 years. It outlines the implementing and refining of the BSC speech-enabled self-service phone system and the creation of the position of voice portal specialist, focused on creating a balance between cost-saving automation and customer satisfaction.

In 2006, Pitney Bowes invested in a suite software applications, including speech analytics. The speech analytics tool directs users to calls related to
particular topics and allows them to quickly listen to the relevant aspects of the call. Using this functionality, Pitney Bowes has been able to reduce call
transfers, address issues with fee waivers, and identify top issues regarding USPS rate-change calls into the call centers.

This presentation covers successful customer-centric contact center voice deployments at several of the largest financial institutions in Australia. Learn the most critical aspects of application development, implementation, and change management, and how a customer-centric approach — coupled with a technical design, giving the business full control of the customer experience — yields staggering results within 6 months.

You’ve spent time and money developing the best applications for your business, but is the application performing as designed? What needs to be done to ensure exemplary performance under load, stress, soak, business-as-usual, and disaster recovery situations? Are your applications and systems delivering the intended customer experience? How do you know? Discussed are several case studies of customers at some of the largest global contact centers who’ve successfully approached these concerns across several verticals involving IVR, voice biometrics authentication, and speech applications.

The use of robotics, such as the Vgo telepresence robot, is becoming widespread. These types of robots basically represent the user in remote locations. The robot uses text-to-speech synthesis to communicate with those around it. Find out how managers, executives, and students use the robot to navigate through a workspace and interact with its inhabitants.

The benefit of using speech-enabled animated video for teaching language has been well-demonstrated. Animated video captures the attention of the
student, and the professionally recorded audio track provides a pronunciation target, which students attempt to match. Speech recognition provides
an indication of their degree of mastery. Combining 3D video with speech technology provides a more compelling vehicle for language instruction.
This presentation focuses on techniques for integrating cloud-based speech technology with 3D video as a platform for teaching language over the public internet.

This session describe a series of experiments to quantify the impact of headset features on speech recognition accuracy. These experiments, conducted both in the lab and on the road, show that improved perceptual quality from noise reduction, as judged by human listeners, does not necessarily translate into higher recognition accuracy.

This session explains the difference between traditional narrowband audio and wideband audio, outlines the current state of available wideband audio options, and discusses what you need to consider when evaluating wideband audio for both servers and clients/devices. Participants will leave with an understanding of how and where they can use wideband audio to improve their speech applications and create better customer experiences.

This talk describes a new technology that significantly increases the base functionality of speech IVRs. A dedicated intelligence engine, or “brain,” manages each live conversation. This engine integrates a number of general capabilities designed to offer sophisticated yet robust natural language self-service. These capabilities include dynamically tuning statistical language model speech recognition, natural language parsing and interpretation, built-in conversational skills and knowledge, and short- and long-term memory, as well as other cognitive abilities. Several practical examples of this technology are presented.

The assistive agent designed for Baby Boomers and beyond illustrates the various challenges and solutions pertaining to the idea of natural conversation. Problems such as adaptation to task familiarity, conversational move differences as a function of domain distance and history, and the automatic modulation of transitional pleasantries are discussed. Learn about the dilemmas ahead for advanced dialogue systems and how to solve them in a modular, comprehensible way.