The InfoQ Podcast cover image

Generally AI Episode 2: AI-Generated Speech and Music

The InfoQ Podcast

CHAPTER

MIDI Representation and AI-Generated Music

This chapter explores the concept of MIDI representation in AI-generated speech and music. It discusses the use of transformer language models to generate sequences of MIDI notes and the challenges of training data for these models. The chapter also touches on the creation of spectrograms to represent sound and the demonstration of AI's ability to modify sound clips and generate music based on prompts.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner