Skip to main content
Top

2011 | Book

Advances in Commercial Deployment of Spoken Dialog Systems

insite
SEARCH

About this book

Advances in Commercial Deployment of Spoken Dialog Systems covers the peculiarities of commercial deployments of spoken dialog systems, from the tools, standards, and design principles to build them, the infrastructure to deploy them, techniques to monitor, evaluate, and analyze them, and, most importantly, effective strategies to adapt, tune, and optimize them. The book shows to what extent academic spoken dialog system research converges with real-world applications. This academic and practical synergy can be leveraged to build successful and robust spoken dialog applications that are useful when dealing with the dynamics of the ever-changing future user.

Table of Contents

Frontmatter
Chapter 1. Deployed vs. Academic Spoken Dialog Systems
Abstract
After a brief introduction into the architecture of spoken dialog systems, important factors of deployed systems (such as call volume, operating costs, or induced savings) will be reviewed. The chapter also discusses major differences between academic and commercially deployed systems.
David Suendermann
Chapter 2. Paradigms for Deployed Spoken Dialog Systems
Abstract
This chapter covers state-of-the-art paradigms for all the components of deployed spoken dialog systems. With a focus on speech recognition and understanding components as well as dialog management, the specific requirements of deployed systems will be discussed. This includes their robustness against distorted and unexpected user input, their real-time-ability, and the need for standardized interfaces.
David Suendermann
Chapter 3. Measuring Performance of Spoken Dialog Systems
Abstract
Key to the evaluation of spoken dialog systems and the prerequisite to tuning these systems is to properly measure their performance. This chapter reviews common performance metrics distinguishing between subjective, objective, observable, and hidden domains. A special focus is placed on spoken language understanding performance metrics and on the architecture required to gather the data necessary to calculate these metrics.
David Suendermann
Chapter 4. Deployed Spoken Dialog Systems’ Alpha and Omega: Adaptation and Optimization
Abstract
Regular tuning of spoken dialog systems is crucial to achieve maximum performance soon after the original deployment and to keep and improve the performance level during the lifetime of these systems. Often, speech recognition and understanding as well as dialog management are embedded in a continuous optimization and adaptation cycle whose details are explained in the present chapter. In addition, several techniques for quality assurance of transcription and semantic annotation as well as the statistical dialog management optimization techniques Escalator, Engager, and Contender are discussed.
David Suendermann
Backmatter
Metadata
Title
Advances in Commercial Deployment of Spoken Dialog Systems
Author
David Suendermann
Copyright Year
2011
Publisher
Springer New York
Electronic ISBN
978-1-4419-9610-7
Print ISBN
978-1-4419-9609-1
DOI
https://doi.org/10.1007/978-1-4419-9610-7