Speech technologies are the basis for the development of new interfaces between humans and smart phones, computers and devices in smart homes. Building onto the knowledge acquired through several undergraduate academic courses, the objective of this course is to widen the multidisciplinary knowledge of students in the area of man-machine speech communication. In order to understand the algorithms for automatic speech recognition and synthesis, speaker recognition and emotional speech recognition, students should become familiar with the features of human speech and its acoustic and linguistic models. In the practice classes, the students will learn to use software tools for speech signal processing and become familiar with applications based on the man-machine speech communication.

Students become familiar with basic algorithms used in automatic speech recognition (ASR) and in text-to-speech synthesis (TTS). In that way students acquire the fundamental knowledge needed in ASR and TTS development and application. They acquire the knowledge necessary for recording and processing speech signal databases and for understanding the algorithms for automatic speech recognition and synthesis, but also for speaker and emotion recognition, as well as language modules and dialogue systems. At the end of the course students are familiar with the possibilities of ASR and TTS, as well as about the tools for development of applications based on these technologies and are ready to give their professional contribution in this scientific and technical field.

• Introduction to ASR and TTS: history, terminology, perspectives • Speech: producation and perception, nature and characteristics (t-f display + labelling (AlfaNum)) • Speech signal: analysis and types of display on a computer (LPC, MFCC, PLP + visualisation (Matlab)) • Natural language processing: language modelling (n-grams) + HMM (HTK) • Approaches to ASR (DTW, ANN, HMM), acoustical, lexical and linguistic models • Procedures of ASR training: GMM, k-means, VQ, Baum-Welch, ML MMI, MWE MPE (HTK) • Algorithms for ASR decoding: Viterbi, Token passing, N-best (HTK) • Robust ASR methods: VTN, CMN, noise suppression • Text-to-speech synthesis (TTS): language processing, synthesis (concatenative and HMM) • Recognition of speakers and emotions in speech • Dialogue modelling, spoken language understanding (SLU), dialogue systems

Lectures are conducted using Power Point presentations available to students in .pdf format. Presentations with audio content and animations demonstrate and illustrate key details in the lectures. The first part of the lectures is followed by group work of students (exam prerequisite), while the second part is comprised of practical exercises in the Laboratory for Acoustics and Speech Technologies and the Speech Studio of the University of Novi Sad. The students will also write a midterm paper, whose defense is one of the exam prerequisites, and which may represent the basis for a subsequent master thesis. Independent student work is supported through the web portal of the Chair of Telecommunications and Signal Processing - www.ktios.net.