process comments of proofread

[asr1617.git] / asr.tex

diff --git a/asr.tex b/asr.tex
index 273cdfa..938078f 100644 (file)
--- a/asr.tex
+++ b/asr.tex
@@ -1,37 +1,8 @@
 %&asr
 \usepackage[toc,nonumberlist,acronyms]{glossaries}
 \makeglossaries%
-\newacronym{ANN}{ANN}{Artificial Neural Network}
-\newacronym{DCT}{DCT}{Discrete Cosine Transform}
-\newacronym{DHMM}{DHMM}{Duration-explicit \acrlong{HMM}}
-\newacronym{FA}{FA}{Forced alignment}
-\newacronym{GMM}{GMM}{Gaussian Mixture Models}
-\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{LPC}{LPC}{Linear Prediction Coefficients}
-\newacronym{MFCC}{MFCC}{\acrlong{MFC} coefficient}
-\newacronym{MFC}{MFC}{Mel-frequency cepstrum}
-\newacronym{MLP}{MLP}{Multi-layer Perceptron}
-\newacronym{PLP}{PLP}{Perceptual Linear Prediction}
-\newacronym{PPF}{PPF}{Posterior Probability Features}
-\newacronym{ZCR}{ZCR}{Zero-crossing Rate}
-\newacronym{RELU}{ReLU}{Rectified Linear Unit}
-\newglossaryentry{dm}{name={Death Metal},
-       description={is an extreme heavy metal music style with growling vocals and
-       pounding drums}}
-\newglossaryentry{dom}{name={Doom Metal},
-       description={is an extreme heavy metal music style with growling vocals and
-       pounding drums played very slowly}}
-\newglossaryentry{FT}{name={Fourier Transform},
-       description={is a technique of converting a time representation signal to a
-       frequency representation}}
-\newglossaryentry{MS}{name={Mel-Scale},
-       description={is a human ear inspired scale for spectral signals}}
-\newglossaryentry{Viterbi}{name={Viterbi},
-       description={is a dynamic programming algorithm for finding the most likely
-       sequence of hidden states in a \gls{HMM}}}
+\input{acronyms}
+\input{glossaries}
 
 \begin{document}
 \frontmatter{}
@@ -43,51 +14,26 @@
        righttextheader={Supervisor:},
        righttext={Louis ten Bosch},
        pagenr=1]
-\listoftodos[Todo]
 
 \tableofcontents
 
-\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}.
-%
+\glsaddall{}
+\printglossaries{}
 
+\mainmatter{}
 
-%Introduction, leading to a clearly defined research question
 \chapter{Introduction}
-\input{intro.tex}
+\input{intro}
 
 \chapter{Methods}
-\input{methods.tex}
+\input{methods}
 
 \chapter{Conclusion \& Discussion}
-\input{conclusion.tex}
+\input{conclusion}
 
 %(Appendices)
 \appendix
-\input{appendices.tex}
-
-\newpage
-%Glossaries
-\glsaddall{}
-\begingroup
-\let\clearpage\relax
-\let\cleardoublepage\relax
-\printglossaries{}
-\endgroup
+\input{appendices}
 
 \bibliographystyle{ieeetr}
 \bibliography{asr}