The multiple fundamental frequency detection problem and the source separation problem from a single-channel signal containing multiple oscillatory components and a nonstationary noise are both challenging tasks. To extract the fetal electrocardiogram (ECG) from a single-lead maternal abdominal ECG, we need to solve both challenges. We propose a novel method to extract the fetal ECG from a single-lead maternal abdominal ECG, without any additional measurement. The algorithm is composed of three components. First, the maternal and fetal heart rates are estimated by the de-shape short time Fourier transform (STFT), which is a recently proposed nonlinear time-frequency analysis technique. The beat tracking technique is the second component which is applied to accurately obtain the maternal and fetal R peaks. The third component consists of establishing the maternal and fetal ECG waveforms by the nonlocal median. The algorithm is tested on two real databases with the annotation provided by experts (adfecgdb database and CinC2013 database) and a simulated database (fecgsym), and provides the state-of-the-art results. We conclude that with the proposed algorithm, the fetal ECG waveform and the fetal heart rate could be accurately obtained from the single-lead maternal abdominal ECG.
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
Melody extraction in polyphonic musical audio is important for music signal processing. In this paper, we propose a novel streamlined encoder/decoder network that is designed for the task. We make two technical contributions. First, drawing inspiration from a state-of-the-art model for semantic pixelwise segmentation, we pass through the pooling indices between pooling and un-pooling layers to localize the melody in frequency. We can achieve result close to the state-of-the-art with much fewer convolutional layers and simpler convolution modules. Second, we propose a way to use the bottleneck layer of the network to estimate the existence of a melody line for each time frame, and make it possible to use a simple argmax function instead of ad-hoc thresholding to get the final estimation of the melody line. Our experiments on both vocal melody extraction and general melody extraction validate the effectiveness of the proposed model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.