Vorlesung: Computerlinguistik/Phonetik, M.Sc.Leitung: Bernd Möbius
Ort: Geb C 7.2, Seminarraum 1.12
Zeit: Tue 16-18
Beginn: ab 08.11.2016
Geeignet für: M.Sc.
Speech synthesis is an essential component of any system relying on intuitive human-machine communication. Speech synthesis systems are also used in phonetic research to gain further insight into speech production and acoustic properties of speech. This advanced course offers an introduction to text-to-speech (TTS) synthesis systems and strategies. Various approaches to speech synthesis are presented, including formant synthesis, concatenative synthesis, and state-of-the-art corpus-based unit selection synthesis. Linguistic text analysis and natural language processing modules typically included in TTS systems are covered as well. This course will be complemented by a research seminar on voice building (offered by Ingmar Steiner), right after the end of the semester.
Suggested companion text book:
Taylor, Paul: Text-to-Speech Synthesis. Cambridge University Press, 2009.
Further text books:
Dutoit, Thierry: An Introduction to Text-to-Speech Synthesis. Kluwer, 1997.
Möbius, Bernd: German and Multilingual Speech Synthesis. AIMS 7 (4), 2001.
Sproat, Richard (ed.): Multilingual Text-to-Speech Synthesis. Kluwer, 1998.
Entrance requirements: None, but some background in computational linguistics, speech science, or signal processing will be advantageous.
Written exam at the end of the winter semester.
Stellung im Studienplan
M.Sc. LST, specialization course area SS&T; M.Sc. LCT; M.Sc. Inf; M.Sc. CuKT