Audio Engineering Seminar
FEKT-MPA-AESAcad. year: 2020/2021
The course includes topics from advanced methods of analysis and processing of audio signals for applications in acoustics, electroacoustics, musicology, music production, multimedia technologies and virtual reality. These include the use of artificial intelligence, information mining from musical works, sparse signal representations, real-time modeling of analogue and digital sound systems and mechanical and acoustic systems, and modern approaches to sound analysis and synthesis.
Learning outcomes of the course unit
On completing the seminar, students will be able to:
- practice knowledge of modern trends in audio technology development
- assess the possibilities of using advanced audio technologies to solve practical problems
- take advantage of advanced audio technology knowledge in product development
- analyze the impact of advanced sound technologies on the development of audio systems
Students must have basic knowledge from the area of audio signal processing and audio technology at Masters level.
Recommended optional programme components
Recommended or required reading
AGGARWAL, Charu C. Neural networks and deep learning: a textbook. Cham: Springer, 2018, xxiii, 497 stran. (EN)
SMITH, Julius O. (Julius Orion). Physical Audio Signal Processing: for Virtual Musical Instruments and Digital Audio Effects. Lexington]: W3K Publishing, 2010, xxii, 803 s. ISBN 978-0-9745607-2-4. (EN)
BAI, Mingxian, Jeong-Guon IH a Jacob BENESTY. Acoustic array systems: Theory, implementation, and application. Singapore: Wiley, 2013, xix, 516 s. : il. ISBN 978-0-470-82723-9. (EN)
FORNASIER, Massimo. Theoretical foundations and numerical methods for sparse recovery. Berlin: Walter de Gruyter, 2010, x, 340 s. : il. ISBN 978-3-11-022614-0. (EN)
Planned learning activities and teaching methods
Methods of educations are described in the article 7 of the BUT’s Study and Examination Regulation. Teaching methods include seminar. Course is taking advantage of e-learning (Moodle) system.
Assesment methods and criteria linked to learning outcomes
The maximum of 30 points is given upon completion of the theoretical tests in seminar. The maximum of 70 points can be gained by completing the final project.
Language of instruction
1. Introduction to Machine Learning and Time-Series Analysis
2. Audio Signal Analysis Using Machine Learning Techniques
3. Music Information Retrieval
4. Audio Content Analysis
5. Acoustic Analysis of Speech and Voice Pathology
6. Restoration of Clipped Audio Signals
7. Completing Missing Samples in Audio
8. Loudspeaker-Room Response Equalisation
9. Modelling Electroacoustic Transducers
10. Real-Time Modeling of Nonlinear Audio Processing Systems
The aim of the course is to give students an overview of current topics and trends in the field of audio engineering. Students will learn advanced techniques of analysis and processing of audio signals and musical works, including the use of artificial intelligence, modern trends in the area of acoustics solutions, modeling and design of electroacoustic transducers, theoretical and experimental psychoacoustics, virtual reality and other areas. Theoretical knowledge is demonstrated in the course on practical examples and case studies.
Specification of controlled education, way of implementation and compensation for absences
The conditions for the successful course completion are stated in the yearly updated supervisor’s notice.