Teaching
Classroom Teaching
ECE 208/408 (TEE 408) - The Art of Machine Learning - Spring 2023
This is a 4-credit undergraduate/graduate course introducing basic concepts of machine learning through real-world ECE applications. It covers various learning paradigms such as supervised learning, semi-supervised learning, unsupervised learning, and reinforcement learning. It also covers classical and state-of-the-art techniques such as nearest neighbor, decision trees, linear models, support vector machines, Gaussian mixture models, hidden Markov models, ensemble learning, principal component analysis, and various kinds of deep neural networks. This course is hands-on with multiple programming assignments and a final project to solve real-world problems.
ECE 277/477 (AME 277, CSC 264/464, TEE 477) - Computer Audition - Fall 2023 (also taught in Fall 2013-2015, 2017-2019, 2022)
This is a 4-credit undergraduate/graduate course covering current research in the field of computer audition. Topics include audio modeling, audio features, source separation (splitting audio mixtures into individual source tracks), pitch estimation (estimating the pitches played by each instrument), streaming (finding which sounds belong to a single event/source), source localization (finding where the sound comes from), source identification (labeling a sound source), etc.
ECE 272/472 (AME 272, TEE 472) - Audio Signal Processing - Spring 2020 (also taught in Springs 2014-2019)
This is a 4-credit undergraduate/graduate course covering fundamentals and applications of audio digital signal processing. Topics include sampling and quantization, analog to digital converters, time and frequency domains, spectral analysis, vocoding, analysis and synthesis of digital filters, audio effects processing, musical sound synthesis, and other advanced topics in audio signal processing. Implementation of algorithms in Matlab and on dedicated DSP platforms is emphasized. This course is cross listed as AME 272/472, ECE 272/472 and TEE 472.
Tutorials
2023 Winter School on Speech and Audio Processing (WiSSAP 2023) - December 2023
It was my great pleasure to give several lectures at the 16th WiSSAP in IIT Kanpur in India. The audience was awesome and very much engaged! Here are my lectures:
- Introduction to Music Information Retrieval
- Music Rhythm Analysis
- Music Pitch Analysis
- Interactive Music Systems
Computer-Assisted Music-Making Systems: Taxonomy, Review, and Live Coding - November 2023
I co-presented this tutorial together with Dr. Philippe Pasquier from Simon Fraser University and my PhD student Christos Benetatos at ISMIR 2023. This tutorial reviews the design principles, practical applications, taxonomy, and the state-of-the-art research of computer assisted music composition and performance systems. It also features a live coding session on building a real-time musical agent using Euterpe, a prototyping framework for creating music interactions on the web. Our paper about Euterpe can be found here.
A Brief History of Interactive Music Systems - August 2022
I gave a brief review of concepts and developments of interactive music systems at the CAAI International Conference on Artificial Intelligence (CICAI) under Theme 3 – Art and Artificial Intelligence. This was a remote presentation.
Audio-Visual Scene Understanding - June 2021
I co-organized this full-day tutorial with Drs. Di Hu, Yapeng Tian, Lele Chen, Amir Zadeh, Ross K. Maddox, and Chenliang Xu at CVPR 2021. This tutorial aims to cover recent advances in audio-visual learning, from the neuroscience study of humans to the computation models of machine. My presentation was on "Audio Scene Understanding".
Audiovisual Music Processing - November 2019
I gave this tutorial together with Dr. Slim Essid and Dr. Sanjeel Parekh from Telecom ParisTech and my student Bochen Li at the International Society for Music Information Retrieval (ISMIR) Conference in November 2019. This tutorial provides an overview of the emerging research area of audiovisual music processing, covering three main categories of research: 1) music performance analysis, 2) content-based classification and retrieval, and 3) audiovisual music generation. This tutorial features two hands-on case studies. All materials can be downloaded from the above GitHub link.
Automatic Music Transcription - October 2015
I gave this tutorial together with Dr. Emmanouil Benetos from Queen Mary Unviersity of London at the International Society for Music Information Retrieval (ISMIR) Conference in October 2015. This tutorial reviewed the state of the art approaches, datasets, evaluation measures, applications, challenges and research directions of automatic music transcription by the time the tutorial was presented. Slides and affiliated resources can be downloaded at the above link.