Limited-Time Offer: Up to 75% Off Coursera Plus!
7000+ certificate courses from Google, Microsoft, IBM, and many more.
This course teaches learners how to generate music using masked acoustic token modeling. The course covers the application of parallel iterative decoding and acoustic token modeling to music audio synthesis. By guiding generation with selectively masked music token sequences, students can create variations on input music while maintaining style, genre, beat, and instrumentation. The teaching method involves a combination of theoretical concepts and practical applications. This course is intended for individuals interested in music generation, artificial intelligence, and neural audio synthesis.