Robust Adaptation To Non Native Accents In Automatic Speech Recognition

Speech recognition technology is being increasingly employed in human-machine interfaces. A remaining problem however is the robustness of this technology to non-native accents, which still cause considerable difficulties for current systems. In this book, methods to overcome this problem are described. A speaker adaptation algorithm that is capable of adapting to the current speaker with just a few words of speaker-specific data based on the MLLR principle is developed and combined with confidence measures that focus on phone durations as well as on acoustic features. Furthermore, a specific pronunciation modelling technique that allows the automatic derivation of non-native pronunciations without using non-native data is described and combined with the previous techniques to produce a robust adaptation to non-native accents in an automatic speech recognition system.

This volume and its companion volume LNAI 4441 constitute a state-of-the-art survey in the field of speaker classification. Together they address such intriguing issues as how speaker characteristics are manifested in voice and speaking behavior. The nineteen contributions in this volume are organized into topical sections covering fundamentals, characteristics, applications, methods, and evaluation.

Chapters in the first part of the book cover all the essential speech processing techniques for building robust, automatic speech recognition systems: the representation for speech signals and the methods for speech-features extraction, acoustic and language modeling, efficient algorithms for searching the hypothesis space, and multimodal approaches to speech recognition. The last part of the book is devoted to other speech processing applications that can use the information from automatic speech recognition for speaker identification and tracking, for prosody modeling in emotion-detection systems and in other speech processing applications that are able to operate in real-world environments, like mobile communication services and smart homes.

Technology-Enhanced Language Learning for Specialized Domains provides an exploration of the latest developments in technology-enhanced learning and the processing of languages for specific purposes. It combines theoretical and applied research from an interdisciplinary angle, covering general issues related to learning languages with computers, assessment, mobile-assisted language learning, the new language massive open online courses, corpus-based research and computer-assisted aspects of translation. The chapters in this collection include contributions from a number of international experts in the field with a wide range of experience in the use of technologies to enhance the language learning process. The essays have been brought together precisely in recognition of the demand for this kind of specialised tuition, offering state-of-the-art technological and methodological innovation and practical applications. The topics covered revolve around the practical consequences of the current possibilites of mobility for both learners and teachers, as well as the applicability of updated technological advances to language learning and teaching, particularly in specialized domains. This is achieved through the description and discussion of practical examples of those applications in a variety of educational contexts. At the beginning of each thematic section, readers will find an introductory chapter which contextualises the topic and links the different examples discussed. Drawing together rich primary research and empirical studies related to specialized tuition and the processing of languages, Technology-Enhanced Language Learning for Specialized Domains will be an invaluable resource for academics, researchers and postgraduate students in the fields of education, computer assisted language learning, languages and linguistics, and language teaching.

This book covers the state-of-the-art in deep neural-network-based methods for noise robustness in distant speech recognition applications. It provides insights and detailed descriptions of some of the new concepts and key technologies in the field, including novel architectures for speech enhancement, microphone arrays, robust features, acoustic model adaptation, training data augmentation, and training criteria. The contributed chapters also include descriptions of real-world applications, benchmark tools and datasets widely used in the field. This book is intended for researchers and practitioners working in the field of speech processing and recognition who are interested in the latest deep learning techniques for noise robustness. It will also be of interest to graduate students in electrical engineering or computer science, who will find it a useful guide to this field of research.

With contributions by leading scientists in the field, this book gives the first comprehensive overview of the results of the seminal SmartKom project – one of the most advanced multimodal dialogue systems worldwide.

The book presents an excellent overview of the recent developments in the different areas of Robotics, Automation and Control. Through its 24 chapters, this book presents topics related to control and robot design; it also introduces new mathematical tools and techniques devoted to improve the system modeling and control. An important point is the use of rational agents and heuristic techniques to cope with the computational complexity required for controlling complex systems. Through this book, we also find navigation and vision algorithms, automatic handwritten comprehension and speech recognition systems that will be included in the next generation of productive systems developed by man.

This book presents a complete overview of all aspects of audiovisual speech including perception, production, brain processing and technology.