view SMC2015latex/section/dataset.tex @ 65:d756734b5dd9

update dataset section

\section{Syncopation Dataset}
\label{sec:data}

The major outcome of the SynPy toolkit is to provide prediction of the level of syncopation of a certain rhythm pattern, or none if not applicable. As a demonstration, we apply all seven syncopation models on the rhythms in the syncopation perceptual dataset in~\cite{Song15thesis, Song13}. This dataset includes 27 monorhythms in 4/4 meter, 36 monorhythms in 6/8 and 48 polyrhythms in 4/4, altogether 111 rhythm-stimuli. 

\begin{figure*}[t]
\centering
\includegraphics[width=0.85\textwidth]{images/allmodels.pdf}
\caption{Syncopation predictions of seven models for the syncopation dataset. The range of syncopation values for all the rhythm patterns are given for each model. Within each rhythm category, the rhythm patterns are arranged by the tatum-rate (i.e. quarter-note rate, eighth-note rate) then in alphabetic order. For example, in 4/4 monorhythms group the rhythm patterns are from ab, ac, ad, ba, ... to dd, then abab,...,dddd in 4/4 monorhythms group. LHL, PRS, TMC, SG can be only applicable to monorhythms, KTH can be only measure rhythms in duple meter.}
\label{fig:modelpredictions}
\end{figure*}

Figure~\ref{fig:modelpredictions} plots the syncopation predictions of individual model for each rhythm. It shows that each model has different ranges of prediction and applicable scope of rhythm categories (refer to Table~\ref{ta:capabilities}.