Book Image

Voice Application Development for Android

Book Image

Voice Application Development for Android

Overview of this book

Speech technology has been around for some time now. However, it has only more recently captured the imagination of the general public with the advent of personal assistants on mobile devices that you can talk to in your own language. The potential of voice apps is huge as a novel and natural way to use mobile devices. Voice Application Development for Android is a practical, hands-on guide that provides you with a series of clear, step-by-step examples which will help you to build on the basic technologies and create more advanced and more engaging applications. With this book, you will learn how to create useful voice apps that you can deploy on your own Android device in no time at all. This book introduces you to the technologies behind voice application development in a clear and intuitive way. You will learn how to use open source software to develop apps that talk and that recognize your speech. Building on this, you will progress to developing more complex apps that can perform useful tasks, and you will learn how to develop a simple voice-based personal assistant that you can customize to suit your own needs. For more interesting information about the book, visit http://lsi.ugr.es/zoraida/androidspeechbook
Table of Contents (19 chapters)
Voice Application Development for Android
Credits
Foreword
About the Authors
Acknowledgement
About the Reviewers
www.PacktPub.com
Preface
Afterword
Index

Statistical NLU


Hand-crafted grammars are time consuming to develop and prone to errors. Considerable linguistic and engineering expertise is required to develop a grammar with good coverage and optimized performance. Moreover, the rules of a hand-crafted grammar cannot easily cope with the irregular input that is characteristic of spontaneous spoken language. For example, given the recognized words I would like a um flight from Paris to New York on Monday no Tuesday afternoon, our grammar would fail since um and no are not specified in the rules.

A statistical grammar is an alternative to a hand-crafted grammar. Statistical grammars are learned from data and involve collecting and annotating large amounts of relevant language data. Statistical grammars can cope with irregular input as they do not have to match the input exactly but rather assign probabilities indicating the extent to which a structure or a semantic interpretation matches the input. There are different types of statistical...