Music Separation Enhancement with Generative Modeling

Autor:	Schaffer, Noah, Cogan, Boaz, Manilow, Ethan, Morrison, Max, Seetharaman, Prem, Pardo, Bryan
Rok vydání:	2022
Předmět:	Computer Science - Sound Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Despite phenomenal progress in recent years, state-of-the-art music separation systems produce source estimates with significant perceptual shortcomings, such as adding extraneous noise or removing harmonics. We propose a post-processing model (the Make it Sound Good (MSG) post-processor) to enhance the output of music source separation systems. We apply our post-processing model to state-of-the-art waveform-based and spectrogram-based music source separators, including a separator unseen by MSG during training. Our analysis of the errors produced by source separators shows that waveform models tend to introduce more high-frequency noise, while spectrogram models tend to lose transients and high frequency content. We introduce objective measures to quantify both kinds of errors and show MSG improves the source reconstruction of both kinds of errors. Crowdsourced subjective evaluations demonstrate that human listeners prefer source estimates of bass and drums that have been post-processed by MSG. Comment: Accepted to ISMIR 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2208.12387 Zobrazit plný text záznamu View this record from Arxiv