\begin{center}
\includegraphics[scale=0.9]{img/logo_telemeta_1-1.pdf}
- \colorbox{yellow!50}{\large \textbf{\url{http://telemeta.org/}}}
+ \hspace{-3cm}\colorbox{yellow!50}{\Large \textbf{\url{http://telemeta.org/}}}
\vskip1ex
\colorbox{yellow!50}
{ Contact : \href{mailto:guillaume@parisson.com}{guillaume@parisson.com} }
\item Goal : fit the professional requirements from both sound archivists and
researchers in ethnomusicology.
\item First prototype online since 2008 : \emph{Archives sonores du CNRS, Musée de
- l'Homme}: \colorbox{yellow!50}
- {\normalsize \bf $\to$ \hskip4ex \url{http://archives.crem-cnrs.fr}}
+ l'Homme}:
\end{itemize}
+\begin{center}
+ \colorbox{yellow!50} {\normalsize \hskip3ex \bf \url{http://archives.crem-cnrs.fr} \hskip3ex }
+\end{center}
\end{block}
\begin{column}[T]{.49\linewidth}
\begin{block}{TimeSide : open web audio processing framework}
One specificity of the Telemeta architecture is to rely on an external component, \emph{TimeSide}, that offers audio player integration together with low and high level audio signal processing capabilities.
- \fcolorbox{telemetaRed}{yellow!40}{%
- \begin{minipage}{0.8\linewidth}\small
- \vskip1ex
- \begin{itemize}\bf
- \item \url{http://www.timeside.org}
- \end{itemize}
- \vskip1ex
- \end{minipage}
-}
+\begin{center}
+ \colorbox{yellow!50}{\bf \hskip3ex \url{http://www.timeside.org} \hskip3ex }
+\end{center}
\begin{figure}[htbp]
\centering
TimeSide incorporates some state-of-the-art audio feature extraction libraries such as:
\begin{itemize}
- \item Aubio: \url{http://aubio.org} \cite{brossierPhD}
-
- \item Yaafe: \url{http://yaafe.sourceforge.net} \cite{yaafe_ISMIR2010}
- \item Vamp plugins: \url{http://www.vamp-plugins.org} \cite{vamp-plugins}
+ \item \textbf{Aubio:
+ \colorbox{yellow!50}{\hskip1ex \url{http://aubio.org} \hskip1ex }}
+ \cite{brossierPhD}
+ \item \textbf{Yaafe:
+ \colorbox{yellow!50}{\hskip1ex \url{http://yaafe.sourceforge.net}\hskip1ex }}
+ \cite{yaafe_ISMIR2010}
+ \item \textbf{Vamp plugins:
+ \colorbox{yellow!50}{\hskip1ex \url{http://www.vamp-plugins.org}\hskip1ex }}
+ \cite{vamp-plugins}
\end{itemize}
Given the extracted features, every sound item in a given collection can be automatically analyze. The results of this analysis can be displayed as a support to ethnomusicological studies.
Further works lead by the DIADEMS project will incorporate advance Music Information Retrieval methods in order to provide automatic annotation, segmentation and similarity analysis.
- \end{block}
- \begin{block}{Examples}
- \begin{minipage}{0.62\linewidth}
+\end{block}
+\begin{block}{Code Example (Python)}
+\vskip1ex
+ \begin{minipage}{0.6\linewidth}
\begin{lstlisting}
->>> import timeside
+import timeside
+
+# Define some processors:
+decoder = timeside.decoder.FileDecoder('sweep.wav')
+analyzer = timeside.analyzer.Level()
+grapher = timeside.grapher.Spectrogram()
+encoder = timeside.encoder.VorbisEncoder('sweep.ogg')
->>> # Define some processors:
->>> decoder = timeside.decoder.FileDecoder('sweep.wav')
->>> analyzer = timeside.analyzer.Level()
->>> grapher = timeside.grapher.Spectrogram()
->>> encoder = timeside.encoder.VorbisEncoder('sweep.ogg')
+# Then, the magic pipeline:
+(decoder | analyzer | grapher | encoder).run()
->>> # Then, the magic pipeline:
->>> (decoder | analyzer | grapher | encoder).run()
+# Get the results:
+grapher.render(output='image.png')
+for key in analyzer.results.keys():
+ print '%s in %s : %s'% (analyzer.results[key].name,
+ analyzer.results[key].unit,
+ analyzer.results[key].data)
->>> # Get the results:
->>> grapher.render(output='image.png')
->>> for key in analyzer.results.keys():
- print '%s in %s : %s'% (analyzer.results[key].name,
- analyzer.results[key].unit,
- analyzer.results[key].data)
\end{lstlisting}
\end{minipage}
+\hskip2ex
\begin{minipage}{0.32\linewidth}
\begin{center}
\textbf{Results}
\begin{figure}
\centering
\includegraphics{img/spectrogram.png}
+ \caption{Spectrogram (sweep signal)}
\end{figure}
\end{center}
+\vskip5ex
\begin{lstlisting}
Level Analyzer Max:[-6.021]