Vocal activity informed singing voice separation with the iKala dataset

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 instrumen tal accompaniment using vocal activity information. To eval uate its performance, we construct a new publicly available iKala dataset that features longer durations and higher quality than the existing MIR-IK dataset for singing voice separation.Part of it will be used in the MIREX Singing Voice Separa tion task. Experimental results on both the MIR-IK dataset and the new iKala dataset confirmed that the more informed the algorithm is, the better the separation results are.Index Terms-Low-rank and sparse decomposition, singing voice separation, informed source separation

Extract Fetal ECG from Single-Lead Abdominal ECG by De-Shape Short Time Fourier Transform and Nonlocal Median

“…To handle this limitation, we could consider the "joint" approach. Vast majority of recent approaches in multi-pitch estimation and source separation in music now falls within the "joint" category [55], and more and more studies on source separation started to consider pitch information to improve the source separation algorithms [56,57]. Note that although it is intuitive to utilize the IF information to handle the detection and separation problem, this kind of approach has been less studied until recent years, probably because the task of finding IF is by no means easy, especially when there are multiple components.…”

Low-Rank Sparse Representation with Pre-Learned Dictionaries and Side Information for Singing Voice Separation

“…Our experiment was conducted on the iKala dataset [9]. The iKala dataset contains 252 30-second clips of Chinese popular songs in CD quality.…”

“…Finally, we combine the reconstructed voice spectrogram from the vocal annotation. Evaluations on the iKala dataset [9] show its better performance than comparison methods.…”

“…They proposed Low-rank and Sparse representation with Pre-learned Dictionaries (LSPD) for singing voice separation. Chan et al [5] proposed a modified RPCA algorithm. This work represented one of the first attempts to incorporate vocal activity information into the RPCA algorithm, then the vocal activity detection was widely studied [6] [7].…”

Learning to separate vocals from polyphonic mixtures via ensemble methods and structured output prediction

“…The publication of publicly-available datasets such as the MIR1k dataset [13] and iKala dataset [14] have also helped benchmark algorithms. The authors of the iKala dataset also held back a set of songs for testing within the MIREX (Music Information Retrieval Evaluation eXchange) 2014 Singing Voice Separation task 1 , which featured 11 algorithms from 8 different teams.…”