Course Websites
CS 598 GMA - Generative Models for Audio
Last offered Spring 2025
Official Description
Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.
Section Description
This course explores generative models widely used in speech, music, and audio processing. Beginning with foundational concepts like linear predictive models, autoregressive models, and state-space models such as Hidden Markov Models, the course builds a strong understanding of traditional audio signal processing techniques. Building on these basics, students will delve into modern deep learning-based generative models, examining key approaches such as adversarial learning, controlled latent spaces, recurrent models, diffusion models, and others. The course emphasizes comparative analysis to highlight the unique characteristics of each model. Students will also engage in presentation sessions, critically reviewing and discussing key literature in audio generation. Students are expected to know the basics of DSP and machine learning. Hands-on experiences and knowledge of deep learning projects are also strongly recommended. Prerequisite: CS 545. For up-to-date information about CS cours
Related Faculty
Schedule and Instructors
Title | Section | CRN | Type | Hours | Times | Days | Location | Instructor |
---|---|---|---|---|---|---|---|---|
Generative Models for Audio | GMA | 62182 | S15 | 4 | 0930 - 1045 | M W | 1214 Siebel Center for Comp Sci | Minje Kim |