A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering Export

@article{citeulike:3177136, abstract = {This paper proposes a multipitch analyzer called the harmonic temporal structured clustering (HTC) method, that jointly estimates pitch, intensity, onset, duration, etc., of each underlying source in a multipitch audio signal. HTC decomposes the energy patterns diffused in time-frequency space, i.e., the power spectrum time series, into distinct clusters such that each has originated from a single source. The problem is equivalent to approximating the observed power spectrum time series by superimposed HTC source models, whose parameters are associated with the acoustic features that we wish to extract. The update equations of the HTC are explicitly derived by formulating the HTC source model with a Gaussian kernel representation. We verified through experiments the potential of the HTC method}, author = {Kameoka, Hirokazu and Nishimoto, Takuya and Sagayama, Shigeki}, booktitle = {Audio, Speech, and Language Processing, IEEE Transactions on}, citeulike-article-id = {3177136}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TASL.2006.885248}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4100686}, doi = {10.1109/TASL.2006.885248}, journal = {Audio, Speech, and Language Processing, IEEE Transactions on}, keywords = {onset}, number = {3}, pages = {982--994}, posted-at = {2009-05-18 09:49:33}, priority = {2}, title = {A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering}, url = {http://dx.doi.org/10.1109/TASL.2006.885248}, volume = {15}, year = {2007} }

TY - JOUR ID - citeulike:3177136 L3 - citeulike-article-id:3177136 N2 - This paper proposes a multipitch analyzer called the harmonic temporal structured clustering (HTC) method, that jointly estimates pitch, intensity, onset, duration, etc., of each underlying source in a multipitch audio signal. HTC decomposes the energy patterns diffused in time-frequency space, i.e., the power spectrum time series, into distinct clusters such that each has originated from a single source. The problem is equivalent to approximating the observed power spectrum time series by superimposed HTC source models, whose parameters are associated with the acoustic features that we wish to extract. The update equations of the HTC are explicitly derived by formulating the HTC source model with a Gaussian kernel representation. We verified through experiments the potential of the HTC method IS - 3 JF - Audio, Speech, and Language Processing, IEEE Transactions on EP - 994 TI - A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering VL - 15 T2 - Audio, Speech, and Language Processing, IEEE Transactions on SP - 982 KW - onset AU - Kameoka, Hirokazu AU - Nishimoto, Takuya AU - Sagayama, Shigeki PY - 2007/// UR - http://dx.doi.org/10.1109/TASL.2006.885248 ER -