-This thesis present a method of detecting \emph{singing}-voice segments in non
-standard music genres. The research uses existing techniques on extreme styles
-like \gls{dm} and \gls{dom} and achieves a good performance.
-\emph{Singer}-voice recognition and detection has also been attempted with
-similarl positive results. This is founded basis for attempting lyrics
-synchronization and lyrics recognition.
+This thesis presents a method of detecting \emph{singing}-voice segments in non
+standard music genres. Growling singing voices have different acoustic
+characteristics compared to regular singing voices. This research uses existing
+\emph{singing}-voice detection techniques on extreme styles like \gls{dm} and
+\gls{dom} and achieves a good performance. \emph{Singer}-voice recognition and
+detection has also been attempted with similar positive results. This forms a
+strong base for attempting lyrics synchronization and lyrics recognition in
+extreme music styles.
-I would like to thank\ldots
+I would like to thank Louis for the interesting Automatic Speech
+Recognition course and the freedom to choose a research subject of own liking.
+Moreover I would like to thank Chris for the sparring sessions and
+proofreading.