170 likes | 378 Views
Welcome to Computer Audition. Zhiyao Duan. Human Audition. Understanding the environment Communication Entertainment. Computer Audition. Understanding the environment Communication Entertainment – entertain human. Some Key Problems. Sound source identification Source localization
E N D
Welcome to Computer Audition Zhiyao Duan ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Human Audition • Understanding the environment • Communication • Entertainment ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Computer Audition • Understanding the environment • Communication • Entertainment – entertain human ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Some Key Problems • Sound source identification • Source localization • Content understanding • Speech, event, melody, rhythm • Source separation ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Impact on Many Fields • Psycho-acoustics • Machine Learning • Information Retrieval • Computer Audition • Music Cognition • Speech Science • Signal Processing ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Many Applications ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Some Demos • http://www.youtube.com/watch?v=3oGFogwcx-E • http://www.music.informatics.indiana.edu/~craphael/music_plus_one/movies/movies.html ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Soundprism Demo Source 1 Source 2 … Source N Single-channel polyphonic music J. Brahms, Clarinet Quintet in B minor, op.115. 3rd movement
Course Topics • Fundamentals of human audition • Auditory models • Audio features (pitch, timbre, ect.) • Audio modeling techniques • State-of-the-art research topics • Polyphonic pitch analysis • Source separation • Sound identification • …… ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Course Objectives • General understanding of the field • Deep understanding of a sub-field • Able to distill large amount of research into coherent summaries • Able to think critically • Improve presentation skills ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Course Information • Everything is on the website • http://www.ece.rochester.edu/~zduan/teaching/ece492 • Office hour: Thursdays 3-4PM or by appointment • Office: Hopeman 308 ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Assignments • Total (110 points) • Homework (30 points) • Class paper review (20 points) • Presentation of research (15 points) • Literature review (30 points) • Peer feedback (15 points) • No exams ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Grading • No extra credit • No curve … C- C C+ B- B B+ A- A 70 73 77 80 83 87 90 93 110 ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Important Policies • No late homework • Do your own work • Attendance is not taken, but class discussions are very important for learning ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Prerequisites • Signal Processing • ECE 246/446 or ECE 272/472 or equivalent • Matlab programming • Preferred but not required • Machine learning such as SVM, Markov models, clustering, etc. ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013
Textbooks • Required • Research papers provided on the website • References (not required) • Albert S. Bregman, Auditory Scene Analysis: The Perceptual Organization of Sound. The MIT Press, 1990. • DeLiang Wang, and Guy J. Brown, editors. Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. IEEE Press / Wiley-Interscience, 2006. • AnssiKlapuri, and Manuel Davy, editors. Signal Processing Methods for Music Transcription, Springer, 2006. ECE 492 - Computer Audition and Its Applications in Music, Zhiyao Duan 2013