Melody transcription via generative pre-training

12/04/2022
by   Chris Donahue, et al.
0

Despite the central role that melody plays in music perception, it remains an open challenge in music information retrieval to reliably detect the notes of the melody present in an arbitrary music recording. A key challenge in melody transcription is building methods which can handle broad audio containing any number of instrument ensembles and musical styles - existing strategies work well for some melody instruments or styles but not all. To confront this challenge, we leverage representations from Jukebox (Dhariwal et al. 2020), a generative model of broad music audio, thereby improving performance on melody transcription by 20 obstacle in melody transcription is a lack of training data - we derive a new dataset containing 50 hours of melody transcriptions from crowdsourced annotations of broad music. The combination of generative pre-training and a new dataset for this task results in 77 transcription relative to the strongest available baseline. By pairing our new melody transcription approach with solutions for beat detection, key estimation, and chord recognition, we build Sheet Sage, a system capable of transcribing human-readable lead sheets directly from music audio. Audio examples can be found at https://chrisdonahue.com/sheetsage and code at https://github.com/chrisdonahue/sheetsage .

READ FULL TEXT

page 1

page 6

research
06/15/2023

Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music

With the growing amount of musical data available, automatic instrument ...
research
07/30/2018

Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network

Research on automatic music generation has seen great progress due to th...
research
12/01/2020

MusicTM-Dataset for Joint Representation Learning among Sheet Music, Lyrics, and Musical Audio

This work present a music dataset named MusicTM-Dataset, which is utiliz...
research
11/01/2021

Learning To Generate Piano Music With Sustain Pedals

Recent years have witnessed a growing interest in research related to th...
research
04/30/2023

Transfer of knowledge among instruments in automatic music transcription

Automatic music transcription (AMT) is one of the most challenging tasks...
research
09/16/2023

SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription

Guitar tablature is a form of music notation widely used among guitarist...
research
08/26/2020

The Freesound Loop Dataset and Annotation Tool

Music loops are essential ingredients in electronic music production, an...

Please sign up or login with your details

Forgot password? Click here to reset