%&asr
+\usepackage[nonumberlist,acronyms]{glossaries}
+\makeglossaries%
+\newacronym{ANN}{ANN}{Artificial Neural Network}
+\newacronym{HMM}{HMM}{Hidden Markov Model}
+\newacronym{GMM}{GMM}{Gaussian Mixture Models}
+\newacronym{DHMM}{DHMM}{Duration-explicit \acrlong{HMM}}
+\newacronym{HTK}{HTK}{\acrlong{HMM} Toolkit}
+\newacronym{FA}{FA}{Forced alignment}
+\newacronym{MFC}{MFC}{Mel-frequency cepstrum}
+\newacronym{MFCC}{MFCC}{\acrlong{MFC} coefficient}
+\newacronym{IFPI}{IFPI}{International Federation of the Phonographic Industry}
+\newglossaryentry{dm}{name={Death Metal},
+ description={is an extreme heavy metal music style with growling vocals and
+ pounding drums}}
+
\begin{document}
-%Titlepage
+\frontmatter{}
+
\maketitleru[
course={(Automatic) Speech Recognition},
institute={Radboud University Nijmegen},
- authorstext={Author:}]
+ authorstext={Author:},
+ pagenr=1]
\listoftodos[Todo]
-\nocite{*}
+\tableofcontents
+
+%Glossaries
+%\glsaddall{}
+%\printglossaries
+
+\mainmatter{}
+%Berenzweig and Ellis use acoustic classifiers from speech recognition as a
+%detector for singing lines. They achive 80\% accuracy for forty 15 second
+%exerpts. They mention people that wrote signal features that discriminate
+%between speech and music. Neural net
+%\glspl{HMM}~\cite{berenzweig_locating_2001}.
+%
+%In 2014 Dzhambazov et al.\ applied state of the art segmentation methods to
+%polyphonic turkish music, this might be interesting to use for heavy metal.
+%They mention Fujihara (2011) to have a similar \gls{FA} system. This method uses
+%phone level segmentation, first 12 \gls{MFCC}s. They first do vocal/non-vocal
+%detection, then melody extraction, then alignment. They compare results with
+%Mesaros \& Virtanen, 2008~\cite{dzhambazov_automatic_2014}. Later they
+%specialize in long syllables in a capella. They use \glspl{DHMM} with
+%\glspl{GMM} and show that adding knowledge increases alignment (bejing opera
+%has long syllables)~\cite{dzhambazov_automatic_2016}.
+%
+
+
+%Introduction, leading to a clearly defined research question
+\chapter{Introduction}
+\section{Introduction}
+The \gls{IFPI} stated that about $43\%$ of music revenue rises from digital
+distribution. The overtake on physical formats took place somewhere in 2015 and
+since twenty years the music industry has seen significant
+growth~\footnote{\url{http://www.ifpi.org/facts-and-stats.php}}.
+
+A lot of this musical distribution goes via non-official channels such as
+YouTube~\footnote{\url{https://youtube.com}} in which fans of the musical group
+accompany the music with synchronized lyrics so that users can sing or read
+along. Because of this interest it is very useful to device automatic
+techniques for segmenting instrumental and vocal parts of a song and
+apply forced alignment or even lyrics recognition on the audio file.
+
+Such techniques are heavily researched and working systems have been created.
+However, these techniques are designed to detect a clean singing voice. Extreme
+genres such as \gls{dm} are using more extreme vocal techniques such as
+grunting or growling. It must be noted that grunting is not a technique only
+used in extreme metal styles. Similar or equal techniques have been used in
+\emph{Beijing opera}, Japanese \emph{Noh} and but also more western styles like
+jazz singing by Louis Armstrong~\cite{sakakibara_growl_2004}. It might even be
+traced back to viking times. An arab merchant wrote in the tenth
+century~\cite{friis_vikings_2004}:
+
+\begin{displayquote}
+ Never before I have heard uglier songs than those of the Vikings in
+ Slesvig. The growling sound coming from their throats reminds me of dogs
+ howling, only more untamed.
+\end{displayquote}
+
+%A majority of the music is not only instrumental but also contains vocal
+%segments.
+%
+%Music is a leading type of data distributed on the internet. Regular music
+%distribution is almost entirely digital and services like Spotify and YouTube
+%allow one to listen to almost any song within a few clicks. Moreover, there are
+%myriads of websites offering lyrics of songs.
+%
+%\todo{explain relevancy, (preprocessing for lyric alignment)}
+%
+%This leads to the following research question:
+%\begin{center}\em%
+% Are standard \gls{ANN} based techniques for singing voice detection
+% suitable for non-standard musical genres like Death metal.
+%\end{center}
+
+%Literature overview / related work
+\section{Related work}
+The field of applying standard speech processing techniques on music started in
+the late 90s~\cite{saunders_real-time_1996,scheirer_construction_1997} and it
+was found that music has different discriminating features compared to normal
+speech.
+
+Berenzweig and Ellis expanded on the aforementioned research by trying to
+separate singing from instrumental music\cite{berenzweig_locating_2001}.
+
+\todo{Incorporate this in literary framing}%
+~\cite{fujihara_automatic_2006}%
+~\cite{fujihara_lyricsynchronizer:_2011}%
+~\cite{fujihara_three_2008}%
+~\cite{mauch_integrating_2012}%
+~\cite{mesaros_adaptation_2009}%
+~\cite{mesaros_automatic_2008}%
+~\cite{mesaros_automatic_2010}%
+~%\cite{muller_multimodal_2012}%
+~\cite{pedone_phoneme-level_2011}%
+~\cite{yang_machine_2012}%
+
+
+
+\section{Research question}
+It is discutable whether the aforementioned techniques work because the
+spectral properties of a growling voice is different from the spectral
+properties of a clean singing voice. It has been found that growling voices
+have less prominent peaks in the frequency representation and are closer to
+noise then clean singing\cite{kato_acoustic_2013}. This leads us to the
+research question:
+
+\begin{center}\em%
+ Are standard \gls{ANN} based techniques for singing voice detection
+ suitable for non-standard musical genres like \gls{dm}.
+\end{center}
+
+\chapter{Methods}
+%Methodology
+
+%Experiment(s) (set-up, data, results, discussion)
+\section{Data \& Preprocessing}
+To run the experiments data has been collected from several \gls{dm} albums.
+The exact data used is available in Appendix~\ref{app:data}. The albums are
+extracted from the audio CD and converted to a mono channel waveform with the
+correct samplerate \emph{SoX}~\footnote{\url{http://sox.sourceforge.net/}}.
+When the waveforms are finished they are converted to \glspl{MFCC} vectors
+using the \emph{python\_speech\_features}%
+~\footnote{\url{https://github.com/jameslyons/python_speech_features}} package.
+All these steps combined results in thirteen tab separated features per line in
+a file for every source file. Every file is annotated using
+Praat~\cite{boersma_praat_2002} where the utterances are manually aligned to
+the audio. An example of an utterances are shown in
+Figures~\ref{fig:bloodstained,fig:abominations}. It is clearly visible that
+within the genre of death metal there are a lot of different spectral patterns
+visible.
+
+\begin{figure}[ht]
+ \centering
+ \includegraphics[width=.7\linewidth]{cement}
+ \caption{A vocal segment of the \emph{Cannibal Corpse} song
+ \emph{Bloodstained Cement}}\label{fig:bloodstained}
+\end{figure}
+
+\begin{figure}[ht]
+ \centering
+ \includegraphics[width=.7\linewidth]{abominations}
+ \caption{A vocal segment of the \emph{Disgorge} song
+ \emph{Enthroned Abominations}}\label{fig:abominations}
+\end{figure}
+
+The data is collected from two\todo{more in the future}\ studio albums. The first
+band is called \emph{Cannibal Corpse} and has been producing \gls{dm} for almost
+25 years and have been creating the same type every album. The singer of
+\emph{Cannibal Corpse} has a very raspy growls and the lyrics are quite
+comprehensible. The second band is called \emph{Disgorge} and make even more
+violent music. The growls of the lead singer sound more like a coffee grinder
+and are more shallow. The lyrics are completely incomprehensible and therefore
+some parts are not annotated with lyrics because it was too difficult to hear
+what was being sung.
+
+\section{Methods}
+\todo{To remove in final thesis}
+The initial planning is still up to date. About one and a half album has been
+annotated and a framework for setting up experiments has been created.
+Moreover, the first exploratory experiments are already been executed and
+promising. In April the experimental dataset will be expanded and I will try to
+mimic some of the experiments done in the literature to see whether it performs
+similar on Death Metal
+\begin{table}[ht]
+ \centering
+ \begin{tabular}{cll}
+ \toprule
+ Month & Description\\
+ \midrule
+ March
+ & Preparing the data\\
+ & Preparing an experiment platform\\
+ & Literature research\\
+ April
+ & Running the experiments\\
+ & Fiddle with parameters\\
+ & Explore the possibilities for forced alignment\\
+ May
+ & Write up the thesis\\
+ & Possibly do forced alignment\\
+ June
+ & Finish up thesis\\
+ & Wrap up\\
+ \bottomrule
+ \end{tabular}
+ \caption{Outline}
+\end{table}
+
+\todo{Explain why MFCC and which parameters}
+\todo{Spectrals might be enough, no decorrelation}
+
+\section{Experiments}
+
+\section{Results}
+
+
+\chapter{Conclusion \& Discussion}
+%Discussion section
+\todo{Novelty}
+\todo{Weaknesses}
+\todo{Dataset is not very varied but\ldots}
+
+\todo{Doom metal}
+%Conclusion section
+%Acknowledgements
+%Statement on authors' contributions
+%(Appendices)
+\appendix
+\chapter{Experimental data}\label{app:data}
+\begin{table}[h]
+ \centering
+ \begin{tabular}{cllll}
+ \toprule
+ Num. & Artist & Album & Song & Duration\\
+ \midrule
+ 00 & Cannibal Corpse & A Skeletal Domain & High Velocity Impact Spatter & 04:06.91\\
+ 01 & Cannibal Corpse & A Skeletal Domain & Sadistic Embodiment & 03:17.31\\
+ 02 & Cannibal Corpse & A Skeletal Domain & Kill or Become & 03:50.67\\
+ 03 & Cannibal Corpse & A Skeletal Domain & A Skeletal Domain & 03:38.77\\
+ 04 & Cannibal Corpse & A Skeletal Domain & Headlong Into Carnage & 03:01.25\\
+ 05 & Cannibal Corpse & A Skeletal Domain & The Murderer's Pact & 05:05.23\\
+ 06 & Cannibal Corpse & A Skeletal Domain & Funeral Cremation & 03:41.89\\
+ 07 & Cannibal Corpse & A Skeletal Domain & Icepick Lobotomy & 03:16.24\\
+ 08 & Cannibal Corpse & A Skeletal Domain & Vector of Cruelty & 03:25.15\\
+ 09 & Cannibal Corpse & A Skeletal Domain & Bloodstained Cement & 03:41.99\\
+ 10 & Cannibal Corpse & A Skeletal Domain & Asphyxiate to Resuscitate & 03:47.40\\
+ 11 & Cannibal Corpse & A Skeletal Domain & Hollowed Bodies & 03:05.80\\
+ 12 & Disgorge & Parallels of Infinite Torture & Revealed in Obscurity & 05:13.20\\
+ 13 & Disgorge & Parallels of Infinite Torture & Enthroned Abominations & 04:05.39\\
+ 14 & Disgorge & Parallels of Infinite Torture & Atonement & 02:57.36\\
+ 15 & Disgorge & Parallels of Infinite Torture & Abhorrent Desecration of Thee Iniquity & 04:17.20\\
+ 16 & Disgorge & Parallels of Infinite Torture & Forgotten Scriptures & 02:01.72\\
+ 17 & Disgorge & Parallels of Infinite Torture & Descending Upon Convulsive Devourment & 04:38.85\\
+ 18 & Disgorge & Parallels of Infinite Torture & Condemned to Sufferance & 04:57.59\\
+ 19 & Disgorge & Parallels of Infinite Torture & Parallels of Infinite Torture & 05:03.33\\
+ 20 & Disgorge & Parallels of Infinite Torture & Asphyxiation of Thee Oppressed & 05:42.37\\
+ 21 & Disgorge & Parallels of Infinite Torture & Ominous Sigils of Ungodly Ruin & 04:59.15\\
+ \bottomrule
+ \end{tabular}
+ \caption{Songs used in the experiments}
+\end{table}
+
\bibliographystyle{ieeetr}
\bibliography{asr}
\end{document}
repositories / asr1617.git / blobdiff