00961nas a2200157 4500008004100000245007700041210006900118260003800187520044500225653002000670653001700690100002100707700001900728700002000747856003600767 2013 eng d00aEnhanced peak picking for onset detection with recurrent neural networks0 aEnhanced peak picking for onset detection with recurrent neural aPrague, Czech RepubliccSeptember3 a
We present a new neural network based peak-picking algorithm for common onset detection functions. Compared to existing hand-crafted methods it yields a better performance and leads to a much lower number of false negative detections. The performance is evaluated on basis of a huge dataset with over 25k annotated onsets and shows a significant improvement over existing methods in cases of signals with previously unknown levels.
10aonset detection10apeak-picking1 aBöck, Sebastian1 aSchlüter, Jan1 aWidmer, Gerhard uhttp://phenicx.upf.edu/node/11001409nas a2200169 4500008004100000245008000041210006900121260003100190520085100221653002201072653002001094653002401114653002401138100002101162700002001183856003601203 2013 eng d00aLocal Group Delay based Vibrato and Tremolo Suppression for Onset Detection0 aLocal Group Delay based Vibrato and Tremolo Suppression for Onse aCuritiba, BrazilcNovember3 aWe present SuperFlux - a new onset detection algorithm with vibrato suppression. It is an enhanced version of the universal spectral flux onset detection algorithm, and reduces the number of false positive detections considerably by tracking spectral trajectories with a maximum filter. Especially for music with heavy use of vibrato (e.g., sung operas or string performances), the number of false positive detections can be reduced by up to 60% without missing any additional events. Algorithm performance was evaluated and compared to state-of-the-art methods on the basis of three different datasets comprising mixed audio material (25,927 onsets), violin recordings (7,677 onsets) and operatic solo voice recordings (1,448 onsets). Due to its causal nature, the algorithm is applicable in both offline and online real-time scenarios.
10alocal group delay10aonset detection10atremolo suppression10avibrato suppression1 aBöck, Sebastian1 aWidmer, Gerhard uhttp://phenicx.upf.edu/node/10901434nas a2200157 4500008004100000245005900041210005900100260003300159520094500192653001901137653002001156653002401176100002101200700002001221856003501241 2013 eng d00aMaximum Filter Vibrato Suppression for Onset Detection0 aMaximum Filter Vibrato Suppression for Onset Detection aMaynooth, IrelandcSeptember3 a
We present SuperFlux - a new onset detection algorithm with vibrato suppression. It is an enhanced version of the universal spectral flux onset detection algorithm, and reduces the number of false positive detections considerably by tracking spectral trajectories with a maximum filter. Especially for music with heavy use of vibrato (e.g., sung operas or string performances), the number of false positive detections can be reduced by up to 60% without missing any additional events. Algorithm performance was evaluated and compared to state-of-the-art methods on the basis of three different datasets comprising mixed audio material (25,927 onsets), violin recordings (7,677 onsets) and operatic solo voice recordings (1,448 onsets). Due to its causal nature, the algorithm is applicable in both offline and online real-time scenarios.
10amaximum filter10aonset detection10avibrato suppression1 aBöck, Sebastian1 aWidmer, Gerhard uhttp://phenicx.upf.edu/node/8800469nas a2200133 4500008004100000245006300041210006300104260003800167653003400205653002000239100001900259700002100278856003600299 2013 eng d00aMusical Onset Detection with Convolutional Neural Networks0 aMusical Onset Detection with Convolutional Neural Networks aPrague, Czech RepubliccSeptember10aconvolutional neural networks10aonset detection1 aSchlüter, Jan1 aBöck, Sebastian uhttp://phenicx.upf.edu/node/111