The Arts

Msanii: High Fidelity Music Synthesis on a Shoestring Budget

K. Maina

Discover Msanii, a groundbreaking model for creating stunningly high-fidelity music with long duration and efficiency. Authored by Kinyugo Maina, this innovative approach utilizes mel spectrograms and diffusion models to generate seamless audio experiences without traditional synthesis methods. Dive into the future of music synthesis!

00:00

Playback language: English

Index

Abstract

This paper introduces Msanii, a novel diffusion-based model for efficient, long-context, high-fidelity music synthesis. It combines mel spectrograms, diffusion models, and neural vocoders to generate tens of seconds of stereo music at 44.1 kHz without concatenative synthesis, cascading architectures, or compression. The model also demonstrates potential for audio inpainting and style transfer.

Publisher

None (Work in Progress)

Published On

Jan 18, 2023

Authors

Kinyugo Maina