Vocal activity informed singing voice separation with the iKala dataset
Lists
Only you see this
Abstract
A new algorithm is proposed for robust principal component analysis with predefined sparsity patterns. The algorithm is then applied to separate the singing voice from the instrumental accompaniment using vocal activity information. To evaluate its performance, we construct a new publicly available iKala dataset that features longer durations and higher quality than the existing MIR-1K dataset for singing voice separation. Part of it will be used in the MIREX Singing Voice Separation task. Experimental results on both the MIR-1K dataset and the new iKala dataset confirmed that the more informed the algorithm is, the better the separation results are.
BibTeX
@inproceedings{chan2015vocal,
author = {Tak-Shing Chan and Tzu-Chun Yeh and Zhe-Cheng Fan and Hung-Wei Chen and Li Su and Yi-Hsuan Yang and Jyh-Shing Roger Jang},
title = {{Vocal activity informed singing voice separation with the iKala dataset}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2015},
url = {https://openreview.net/forum?id=pA9jetr3Vp},
}Loading related content...