Bøger af Wolfgang Minker

This extensive study of new statistical approaches that allow recognition of negative dialog patterns in SDS fosters a flexible, portable and accurate approach to the topic, using methods based on acoustic, linguistic, and contextual features in spoken dialog.

Presenting a new framework for managing adaptive spoken dialogue systems that will enhance environmental interactivity, this volume also includes test results on the prototype and detailed data evaluation that represent a significant contribution to research.

As speech resources for dialectal Arabic speech recognition are very sparse, this book will be widely welcomed, using Egyptian colloquial Arabic (ECA) as a typical dialect and providing a high-quality ECA speech corpus with accurate phonetic transcription.

Stochastically-Based Semantic Analysis investigates the problem of automatic natural language understanding in a spoken language dialog system.

This volume provides a logic-based reasoning component for spoken language dialogue systems. The text describes late-breaking research on next-generation spoken dialogue systems and investigates how to improve them.

This book introduces a general framework for adapting multimodal interactive systems. It investigates how multimodal, interactive systems may be improved in terms of usability and user friendliness as well as describes exhaustive user tests.

The authors set out the theory and methods for quality enhancement of clean and distorted speech signals such as those that have undergone a band limitation in a telephone network. Problems and solutions are discussed for the different approaches.

This book addresses the problem of separating spontaneous multi-party speech by way of microphone arrays (beamformers) and adaptive signal processing techniques. All experimental results have been obtained with real in-car microphone recordings involving simultaneous speech of the driver and the co-driver.

Current speech recognition systems are based on speaker independent speech models and suffer from inter-speaker variations in speech signal characteristics. This work develops an integrated approach for speech and speaker recognition.

This book presents a fully statistical approach for modeling the pronunciation of non-native speakers, using a proven and tested method based on a discrete hidden Markov model as a word pronunciation model, initialized on a standard pronunciation dictionary.

The subject of this study is the role of hierarchical structures, based on neural networks, in identifying phonemes in automated speech recognition systems. It shows how the artificial neural network paradigm can simplify the analysis of spoken language.

This book presents novel methods to perform robust speech-based emotion recognition at low complexity. It describes a flexible dialogue model to conveniently integrate emotions and other dialogue-influencing parameters in human-computer interaction.

This book describes spoken dialogue systems that act as independent dialogue partners in the conversation with and between users. It presents novel methods for dialogue history and dialogue management.

The authors address the problem of developing efficient automatic speech recognition systems that maintain a balance between utilizing a wide knowledge of speech variability, while keeping the training manageable and improving speech recognition performance.

Speech and Human-Machine Dialog focuses on the dialog management component of a spoken language dialog system. These systems are of special interest for interactive applications, and they integrate several technologies including speech recognition, natural language understanding, dialog management and speech synthesis.

Stochastically-Based Semantic Analysis investigates the problem of automatic natural language understanding in a spoken language dialog system.