Contents This lecture first gives an overview on basic mechanisms of human speech production and perception and then presents in detail an introduction in statistical oriented methods for automatic speech recognition. Main topics in this lecture are feature extraction, vector quantization, acoustical modeling with the help of Hidden Markov Models, linguistic modeling of language with stochastic grammars, prosodic information and search algorithms for the acceleration of the decoding step in a speech recogniton system.

 

Literature

• Niemann H.: Klassifikation von Mustern; Springer, Berlin 1983

• Niemann H.: Pattern Analysis and Understanding; Springer, Berlin 1990

• Schukat-Talamazzini E.G.: Automatische Spracherkennung; Vieweg, Wiesbaden 1995

• Rabiner L.R., Schafer R.: Digital Processing of Speech Signals; Prentice Hall, New Jersey 1978

• Rabiner L.R., Juang B.H.: Fundamentals of Speech Recognition; Prentice Hall, New Jersey 1993