In this paper we describe our submission for the audio melody extraction task of the Music Information Retrieval Evaluation eXchange (MIREX) 2011 campaign. The system presented here is an updated version of the one submitted to last year's campaign. Following a detailed analysis of each step of our method, system parameters have been optimised for melody extraction and the implementation is now more efficient. Two variants of the system have been submitted, each making use of a different spectral transform, allowing us to asses whether the difference between them is significant for overall performance.Following the description of the system, we describe the data-sets and metrics used for evaluation. This is followed by a summary of the results and some conclusions.
Background and Aims: Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real-time to predict future glucose levels in order to prevent hypo/hyperglycemic events. This paper proposes a new on-line method for predicting future glucose concentration levels from CGM data.
Methods:The predictor is implemented with an artificial neural network model (NNM). The inputs of the NNM are the values provided by the CGM sensor during the preceding 20 minutes, while the output is the prediction of glucose concentration at the chosen prediction horizon (PH) time. The method performance is assessed using datasets from two different CGM systems (9 subjects using the Medtronic Guardian and 6 subjects using the Abbott Navigator). Three different PH are used, i.e. 15, 30 and 45 minutes. The NNM accuracy has been estimated by using the root mean square error (RMSE) and prediction delay.
Results:The RMSE is around 10, 18 and 27 mg/dl for 15, 30 and 45 minutes of PH, respectively. The prediction delay is around 4, 9 and 14 minutes for upward trends and 5, 15 and 26 minutes for downward trends, respectively. A comparison with a previously published technique, based on an autoregressive model (ARM) [1], has been performed. The comparison shows that, the proposed NNM is more accurate than the ARM, with no significant deterioration in the prediction delay.
Conclusions:The proposed NNM is a reliable solution for the on-line prediction of future glucose concentrations from CGM data.
Abstract-We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of the same underlying musical piece). Cover song identification is a task whose popularity has increased in the Music Information Retrieval (MIR) community along in the past, as it provides a direct and objective way to evaluate music similarity algorithms. This article first presents a series of experiments carried out with two state-of-the-art methods for cover song identification. We have studied several components of these (such as chroma resolution and similarity, transposition, beat tracking or Dynamic Time Warping constraints), in order to discover which characteristics would be desirable for a competitive cover song identifier. After analyzing many cross-validated results, the importance of these characteristics is discussed, and the best-performing ones are finally applied to the newly proposed method. Multiple evaluations of this one confirm a large increase in identification accuracy when comparing it with alternative state-of-the-art approaches.
Abstract. In this paper we introduce a low-latency monaural source separation framework using a Convolutional Neural Network (CNN). We use a CNN to estimate time-frequency soft masks which are applied for source separation. We evaluate the performance of the neural network on a database comprising of musical mixtures of three instruments: voice, drums, bass as well as other instruments which vary from song to song. The proposed architecture is compared to a Multilayer Perceptron (MLP), achieving on-par results and a significant improvement in processing time. The algorithm was submitted to source separation evaluation campaigns to test efficiency, and achieved competitive results.
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.