Springer, 2008. — 403 p.
The remarkable advances in computing and networking have sparked an enormous interest in deploying Automatic Speech Recognition on Mobile Devices and Over Communication Networks, and the trend is accelerating. This yields an abundance of practical systems, operational algorithms and scientific publications. There is, however, no integrated book available that portrays the whole picture of this area. Our primary impetus for editing this book is to fill this gap by providing a comprehensive and unified introduction to the field.
The prevalence of mobile devices, coupled with the proliferation of wireless networks, creates new opportunities for speech recognition technology. Mobile devices are small in size and are used while on the move, both of which make speech-enabled user interfaces attractive in comparison with other interaction modes like keypad and stylus. The opportunities come along with challenges as well. For instance, it is not an easy task to port state-of-the-art speech recognition systems onto computationally limited devices such as mobile phones, PDAs and automobiles where they are highly desirable. Fortunately, the barriers are being removed because of increasingly powerful embedded platforms and pervasive network connections. Still, however, the accompanying research and engineering issues are many: computational constraints and power limitations on the devices, speech coding and transmission deteriorations over the networks, diverse operating systems and hardware configurations, to name just a few. To address these issues requires a wide scope of knowledge and experience.
This book brings together leading researchers and practitioners from academia and industry to provide an in-depth review of methods and standards, share working knowledge, and present state-of-the-art systems and applications. We cover network speech recognition, distributed speech recognition and embedded speech recognition, which are expected to co-exist in the coming years.
Network, Distributed and Embedded Speech Recognition: An Overview
Network Speech RecognitionSpeech Coding and Packet Loss Effects on Speech and Speaker Recognition
Speech Recognition Over Mobile Networks
Speech Recognition Over IP Networks
Part II Distributed Speech RecognitionDistributed Speech Recognition Standards
Speech Feature Extraction and Reconstruction
Quantization of Speech Features: Source Coding
Error Recovery: Channel Coding and Packetization
Error Concealment
Embedded Speech RecognitionAlgorithm Optimizations: Low Computational Complexity
Algorithm Optimizations: Low Memory Footprint
Fixed-Point Arithmetic
Systems and ApplicationsSoftware Architectures for Networked Mobile Speech Applications
Speech Recognition in Mobile Phones
Handheld Speech to Speech Translation System
Automotive Speech Recognition
Energy Aware Speech Recognition for Mobile Devices