Professionally-produced Music Separation Guided by Covers
نویسندگان
چکیده
This paper addresses the problem of demixing professionally produced music, i.e., recovering the musical source signals that compose a (2-channel stereo) commercial mix signal. Inspired by previous studies using MIDI synthesized or hummed signals as external references, we propose to use the multitrack signals of a cover interpretation to guide the separation process with a relevant initialization. This process is carried out within the framework of the multichannel convolutive NMF model and associated EM/MU estimation algorithms. Although subject to the limitations of the convolutive assumption, our experiments confirm the potential of using multitrack cover signals for source separation of commercial music.
منابع مشابه
The 2015 Signal Separation Evaluation Campaign
In this paper, we report the 2015 community-based Signal Separation Evaluation Campaign (SiSEC 2015). This SiSEC consists of four speech and music datasets including two new datasets: “Professionally produced music recordings” and “Asynchronous recordings of speech mixtures”. Focusing on them, we overview the campaign specifications such as the tasks, datasets and evaluation criteria. We also s...
متن کاملA Comparison of Sound Segregation Techniques for Predominant Instrument Recognition in Musical Audio Signals
The authors address the identification of predominant music instruments in polytimbral audio by previously dividing the original signal into several streams. Several strategies are evaluated, ranging from low to high complexity with respect to the segregation algorithm and models used for classification. The dataset of interest is built from professionally produced recordings, which typically p...
متن کاملMultichannel nonnegative matrix factorization in convolutive mixtures for audio source separation Factorisation en matrices à coefficients positifs de données multicanal convolutives pour la séparation de sources audio
We consider inference in a general data-driven object-based model of multichannel audio data, assumed generated as a possibly underdetermined convolutive mixture of source signals. We work in the Short-Time Fourier Transform (STFT) domain, where convolution is routinely approximated as linear instantaneous mixing in each frequency band. Each source STFT is given a model inspired from nonnegativ...
متن کاملPanel: Standards from the Computer Music Community
This panel discussion will review the standards that the computer music community has produced and how these standards were created, followed by a guided interactive group discussion about future directions for our community in terms of old and new standards.
متن کاملBioactivity-Guided Separation of an α-Amylase Inhibitor Flavonoid from Salvia virgata
It is now believed that the inhibition of carbohydrate hydrolyzing enzymes (CHEs) in the digestive tract can significantly prolong the overall carbohydrate digestion time and decrease the postprandial hyperglycemia after a meal. Therefore, inhibitors of CHEs can be useful therapeutic approaches in the management of diabetes mellitus, especially in the type 2, and complications associated with t...
متن کامل