The book explains the essential approaches to speech synthesis and speech recognition and conveys the relevant foundational knowledge. This includes, in particular: basic knowledge about human speech production and perception, characteristics of speech signals and their representation, fundamental knowledge in linguistics, especially phonetics, morphology, and syntax, the most important transformations and methods of digital speech signal processing, statistical approaches to describe multidimensional quantities and complex relationships (Hidden Markov Models and neural networks), as well as the formulation and application of knowledge in the form of rules. The second edition of the book includes a new chapter on polyglot speech synthesis, which can read mixed-language text correctly. Additionally, the latest approaches for both speech signal production and speech recognition are introduced.