true final

[asr1617.git] / results.tex

diff --git a/results.tex b/results.tex
index d6cf238..1f13895 100644 (file)
--- a/results.tex
+++ b/results.tex
@@ -1,53 +1,61 @@
 \section{\emph{Singing}-voice detection}
-Table~\ref{tbl:singing} shows the results for the singing-voice detection.
-Figure~\ref{fig:bclass} shows an example of a segment of a song with the
-classifier plotted underneath to illustrate the performance. The performance is
-given by the accuracy and loss. The accuracy is the percentage of correctly
-classified samples.
+Table~\ref{tbl:singing} shows the results for the singing-voice detection. The
+performance is given by the fraction of correctly classified samples
+(accuracy). The rows represent the count of hidden nodes, the columns represent
+the analysis window step size and the analysis window length in the \gls{MFCC}
+extraction. A ceiling effect was observed after two epochs for every hidden
+node configuration.
 
 \begin{table}[H]
        \centering
-       \begin{tabular}{rccc}
+       \begin{tabular}{rrccc}
                \toprule
-                  & \multicolumn{3}{c}{Parameters (step/length)}\\
-                   & 10/25 & 40/100 & 80/200\\
+                  & & \multicolumn{3}{c}{Parameters (step/length)}\\
+                  & & 10/25 & 40/100 & 80/200\\
                \midrule
                \multirow{4}{*}{Hidden Nodes}
-                & 0.86 (0.34) & 0.87 (0.32) & 0.85 (0.35)\\
-                & 0.87 (0.31) & 0.88 (0.30) & 0.87 (0.32)\\
-                & 0.88 (0.30) & 0.88 (0.31) & 0.88 (0.29)\\
-                & 0.89 (0.28) & 0.89 (0.29) & 0.88 (0.30)\\
+                & 3 & 0.86 (0.34) & 0.87 (0.32) & 0.85 (0.35)\\
+                & 5 & 0.87 (0.31) & 0.88 (0.30) & 0.87 (0.32)\\
+                & 8 & 0.88 (0.30) & 0.88 (0.31) & 0.88 (0.29)\\
+                & 13 & 0.89 (0.28) & 0.89 (0.29) & 0.88 (0.30)\\
                \bottomrule
        \end{tabular}
-       \caption{Binary classification results (accuracy
-               (loss))}\label{tbl:singing}
+       \caption{Binary classification results (accuracy (loss))}%
+       \label{tbl:singing}
 \end{table}
 
-Plotting the classifier under a segment of the data results in
-Figure~\ref{fig:bclass}.
+Figure~\ref{fig:bclass} shows an example of a segment of a song with the
+classifier plotted underneath. For this illustration the $13$ node model is
+used with a analysis window size and step of $40$ and $100$ respectively. The
+output is smoothed using a hanning window. This figure shows that the model
+focusses on the frequencies around $300Hz$ which contain the growling. When
+there is a little silence in between the growls the classifier immediately
+drops. This phenomenon is visible throughout the songs.
 
 \begin{figure}[H]
        \centering
-       \includegraphics[width=.7\linewidth]{bclass}.
+       \includegraphics[width=1\linewidth]{bclass}
        \caption{Plotting the classifier under the audio signal}\label{fig:bclass}
 \end{figure}
 
 \section{\emph{Singer}-voice detection}
 Table~\ref{tbl:singer} shows the results for the singer-voice detection. The
-same metrics are used as in \emph{Singing}-voice detection.
+same metrics are used as in \emph{Singing}-voice detection. In these
+experiment a ceiling effect was observed after two to three epochs for every
+hidden node configuration.
 
 \begin{table}[H]
        \centering
-       \begin{tabular}{rccc}
+       \begin{tabular}{rrccc}
                \toprule
-                  & \multicolumn{3}{c}{Parameters (step/length)}\\
-                   & 10/25 & 40/100 & 80/200\\
+                  & & \multicolumn{3}{c}{Parameters (step/length)}\\
+                  & & 10/25 & 40/100 & 80/200\\
                \midrule
                \multirow{4}{*}{Hidden Nodes}
-                & 0.83 (0.48) & 0.82 (0.48) & 0.82 (0.48)\\
-                & 0.85 (0.43) & 0.84 (0.44) & 0.84 (0.44)\\
-                & 0.86 (0.41) & 0.86 (0.39) & 0.86 (0.40)\\
-                & 0.87 (0.37) & 0.87 (0.38) & 0.86 (0.39)\\
+                & 3 & 0.83 (0.48) & 0.82 (0.48) & 0.82 (0.48)\\
+                & 5 & 0.85 (0.43) & 0.84 (0.44) & 0.84 (0.44)\\
+                & 8 & 0.86 (0.41) & 0.86 (0.39) & 0.86 (0.40)\\
+                & 13 & 0.87 (0.37) & 0.87 (0.38) & 0.86 (0.39)\\
                \bottomrule
        \end{tabular}
        \caption{Multiclass classification results (accuracy
@@ -84,6 +92,6 @@ singing.
 \begin{figure}[H]
        \centering
        \includegraphics[width=.7\linewidth]{alien2}.
-       \caption{Plotting the classifier with alien data containing strange vocal
-       styles}\label{fig:alien2}
+       \caption{Plotting the classifier with alien data containing unobserved
+       vocal styles}\label{fig:alien2}
 \end{figure}