Speech Recognition Over Digital Channels: Robustness and Standards (Repost)

Automatic speech recognition (ASR) is a very attractive means forhuman-machine interaction. The degree of maturity reached by speechrecognition technologies during recent years allows the developmentof applications that use them. In particular, ASR shows an enormouspotential in mobile environments, where devices such as mobilephones or PDAs are used, and for Internet Protocol (IP)applications.
Speech Recognition Over Digital Channels is the firstbook of its kind to offer a complete system comprehension,addressing the topics of distributed and network-based speechrecognition issues and standards, the concepts of speech processingand transmission, and system architectures and robustness.
Describes the different client/server architectures for remotespeech recognition systems, by means of which the client transmitsspeech parameters through a digital channel to a remote recognitionserver
- Focuses on robustness against both adverse acousticenvironments (in the front-end) and bit errors/packet loss
- Discusses four ETSI standards for distributed speechrecognition; the understanding of the standards and thetechnologies behind them
- Provides the necessary background for the comprehension ofremote speech recognition technologies
This book will appeal to a wide-ranging audience: engineersusing speech recognition systems, researchers involved in ASRsystems and those interested in processing and transmitting speechsuch as signal processing and communications communities. It willalso be of interest to technical experts requiring an understandingof recognition over mobile and IP networks, and postgraduatestudents working on robust speech processing.