This book constitutes the proceedings of the 20th International Conference on Text, Speech, and Dialogue, TSD 2017, held in Prague, CzechRepublic, in August 2017. The 56 regular papers presented together with 3 abstracts of keynote talks were carefully reviewed and selected from 117 submissions. They focus on topics such as corpora and language resources; speech recognition; tagging, classification and parsing of text and speech; speech and spoken language generation; semantic processing of text and speech; integrating applications of text and speech processing; automatic dialogue systems; as well as multimodal techniques and modelling.

This book constitutes of the major results of the EU COST (European Cooperation in the field of Scientific and Technical Research) Action 277: NSP, Nonlinear Speech Processing, running from April 2001 to June 2005. Coverage includes such areas as speech analysis for speech synthesis, speech recognition, speech-non speech discrimination and voice quality assessment, speech enhancement, and emotional state detection.

The book is a collection of invited chapters by experts in Chinese document and text processing, and is part of a series on Language Processing, Pattern Recognition, and Intelligent Systems. The chapters introduce the latest advances and state-of-the-art methods for Chinese document image analysis and recognition, font design, text analysis and speaker recognition. Handwritten Chinese character recognition and text line recognition are at the core of document image analysis (DIA), and therefore, are addressed in four chapters for different scripts (online characters, offline characters, ancient characters, and text lines). Two chapters on character recognition pay much attention to deep convolutional neural networks (CNNs), which are widely used and performing superiorly in various pattern recognition problems. A chapter is contributed to describe a large handwriting database consisting both online and offline characters and text pages. Postal mail reading and writer identification, addressed in two chapters, are important applications of DIA. The collection can serve as reference for students and engineers in Chinese document and text processing and their applications.