Speech Technologies

Higher education teachers: Mihelič France

Subject description

Prerequisits:

• Completed undergraduate study programme in the field of electrical engineering or related engineering or natural and mathematical sciences.
• Enrolment in the 2nd year of the Master’s study programme of Electrical Engineering (2nd cycle).
• Basic knowledge of applied mathematics (vectors and matrices, eigenvectors and eigenvalues, some linear algebra, multivariate analysis, probability theory, and statistics).

Content (Syllabus outline):

Introduction: description of the field, short outline of the historical development of speech technologies. Importance and developments of speech technologies applications for Slovenian language.

Basic characteristics production and auditory perception in human speech communication. Representation of speech patterns.

Speech processing: acquisition and preprocessing, speech features, speech signal segmentation, speech databases.

Speech recognition systems: speaker recognition and verification, isolated word and continuous speech recognition, spontaneous speech recognition. Statistical acoustic and language modeling, semantic speech analysis.

Artificial speech: systems for speech synthesis in general, grapheme-to-phoneme conversion, prosody modeling, speech-synthesis procedures. Assessment of speech synthesis systems.

Dialogue: automated dialogue systems in general, system configurations, dialogue management, knowledge representations, multimodality, assessment of dialogue systems

Objectives and competences:

The aim of this course is to acquaint students with the field of speech technologies and introduce various algorithms, techniques, and methods to accomplish tasks related to this field.

Intended learning outcomes:

Knowledge about the representation, description, synthesis and recognition of speech signals. Understanding the complexity and interdisciplinarity of the field of speech technologies. Knowledge and understanding of the structure and capabilities of speech- and image-based technologies

Learning and teaching methods:

• Lectures
• Interactive teaching
• Practical assignements
• Seminar work

Study materials

1. Mihelič F., Signali, Založba FE in FRI, Ljubljana, 2014
2. Pavešić N., Razpoznavanje vzorcev: uvod v analizo in razumevanje vidnih in slušnih vzorcev, 3. Popravljena in dopolnjena izdaja, Založba FE in FRI, Ljubljana, 2012
3. Rabiner L., Schafer R., Theory and Applications of Digital Speech Processing, Prentince Hall, 1. Ed., 2010