From: Mart Lubbers <mart@martlubbers.net>
Date: Tue, 30 May 2017 15:35:51 +0000 (+0200)
Subject: elaborate on results and fix typo in acronyms
X-Git-Url: https://git.martlubbers.net/?a=commitdiff_plain;h=b9f787ae8d33ca830f0e3b28aef0a020544f5271;p=asr1617.git

elaborate on results and fix typo in acronyms
---

diff --git a/acronyms.tex b/acronyms.tex
index 5d478e0..d26f028 100644
--- a/acronyms.tex
+++ b/acronyms.tex
@@ -6,7 +6,7 @@
 \newacronym{HMM}{HMM}{Hidden Markov Model}
 \newacronym{HTK}{HTK}{\acrlong{HMM} Toolkit}
 \newacronym{IFPI}{IFPI}{International Federation of the Phonographic Industry}
-\newacronym{LPCC}{LPCC}{\acrlong{LPC} derivec cepstrum}
+\newacronym{LPCC}{LPCC}{\acrlong{LPC} derived cepstrum}
 \newacronym{LPC}{LPC}{Linear Prediction Coefficients}
 \newacronym{MFCC}{MFCC}{\acrlong{MFC} coefficient}
 \newacronym{MFC}{MFC}{Mel-frequency cepstrum}
diff --git a/conclusion.tex b/conclusion.tex
index 97ba7de..96d4fba 100644
--- a/conclusion.tex
+++ b/conclusion.tex
@@ -9,6 +9,12 @@ on alien data that uses similar singing techniques as the training set.
 However, the model does not cope very well with different singing techniques or
 with data that contains a lot of atmospheric noise and accompaniment.
 
+From the results we conclude that the model generalizes well over the trainings
+set, even with little hidden nodes. The models with 3 or 5 hidden nodes score a
+little worse than their bigger brothers but there is hardly any difference
+between the performance of a model with 8 or 13 nodes. Moreover, contrary than
+expected the window size does not seem to be doing much in the performance.
+
 \subsection{Future research}
 \paragraph{Forced aligment: }
 Future interesting research includes doing the actual forced alignment. This
diff --git a/methods.tex b/methods.tex
index 210e135..cb65d48 100644
--- a/methods.tex
+++ b/methods.tex
@@ -212,6 +212,9 @@ batch size of $32$.
 
 \section{Results}
 \subsection{\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.
 
 \begin{table}[H]
 	\centering
@@ -226,16 +229,18 @@ batch size of $32$.
 		13h & 0.89 (0.28) & 0.89 (0.29) & 0.88 (0.30)\\
 		\bottomrule
 	\end{tabular}
-	\caption{Binary classification results (accuracy (loss))}
+	\caption{Binary classification results (accuracy
+		(loss))}\label{tbl:singing}
 \end{table}
 
 \begin{figure}[H]
 	\centering
 	\includegraphics[width=.6\linewidth]{bclass}.
-	\caption{Plotting the classifier under the audio signal}
+	\caption{Plotting the classifier under the audio signal}\label{fig:bclass}
 \end{figure}
 
 \subsection{\emph{Singer} voice detection}
+Table~\ref{tbl:singer} shows the results for the singer-voice detection.
 
 \begin{table}[H]
 	\centering
@@ -250,7 +255,8 @@ batch size of $32$.
 		13h & 0.87 (0.37) & 0.87 (0.38) & 0.86 (0.39)\\
 		\bottomrule
 	\end{tabular}
-	\caption{Multiclass classification results (accuracy (loss))}
+	\caption{Multiclass classification results (accuracy
+		(loss))}\label{tbl:singer}
 \end{table}
 
 \subsection{Alien data}