Deep Learning for Music Information Retrieval

Tuition scholarships available for applicants commited to advancing diversity in STEM. Fill out this form by June 2nd.


Instructors: Irán Román
TAs: Ankita Mitra & Anish Nag


The availability of large-scale databases has facilitated recent advances in Deep Learning across fields like computer vision, genomics, and natural language processing. These techniques are also applied in the field of Music Information Retrieval.

We will master the theory behind tools at the intersection of machine learning, Digital Signal Processing, Music Information Retrieval, and Computational Neuroscience. First we will write software completely from scratch, and then we will optimize our implementations with TensorFlow.

Syllabus:
Day 1: Feature spaces of music. Review of k-means clustering, SVMs, and regression classifiers.
Day 2: Decomposing and building a Softmax Neural Network from scratch, and training it with music.
Day 3: Obtaining Spectral Features from raw audio using Convolutional Neural Networks.
Day 4: Natural Language Processing in Music using Recurrent Neural Networks.
Day 5: Make it your own: Proposing and developing a Final Project with Neural Networks.

Prerequisites:
- CCRMA MIR workshop (any year) or consent from instructor (iran@ccrma_DOT_stanford_DOT_edu).
- Calculus and programming experience with Python
- Recommended: Linear Algebra.

About the instructor: Irán Román studies Computer-based Music Theory at Stanford University's CCRMA (Center for Computer Research in Music and Acoustics), and Computational Neuroscience at the Stanford Neuroscience Institute, carrying out research with Dr. Takako Fujioka. He is also a student in the graduate training program at the Stanford Center for Mind Brain and Computation, carrying out research with Dr. Jay McClelland.

IMPORTANT: Contact the instructor before registering to confirm your eligibility. Attach a copy of your registration or diploma for the CCRMA Music Information Retrieval workshop taught by Steve Tjoa. Describe your experience with python programming (preferably include a link to your github page), and college-level math classes at the level of Calculus I or above.