asr.tex

   1 %&asr
   2 \usepackage[nonumberlist,acronyms]{glossaries}
   3 \makeglossaries%
   4 \newacronym{HMM}{HMM}{Hidden Markov Model}
   5 \newacronym{HTK}{HTK}{\acrlong{HMM} Toolkit}
   6 \newacronym{FA}{FA}{Forced alignment}
   7 \newacronym{MFC}{MFC}{Mel-frequency cepstrum}
   8 \newacronym{MFCC}{MFCC}{\acrlong{MFC} coefficient}
   9 %\newglossaryentry{mTask}{name=mTask,
  10 %       description={is an abstraction for \glspl{Task} living on \acrshort{IoT} devices}}
  11
  12 \begin{document}
  13 %Titlepage
  14 \maketitleru[
  15         course={(Automatic) Speech Recognition},
  16         institute={Radboud University Nijmegen},
  17         authorstext={Author:}]
  18 \listoftodos[Todo]
  19
  20 \tableofcontents
  21
  22 %Glossaries
  23 \glsaddall{}
  24 \printglossaries%
  25
  26 Berenzweig and Ellis use acoustic classifiers from speech recognition as a
  27 detector for singing lines.  They achive 80\% accuracy for forty 15 second
  28 exerpts. They mention people that wrote signal features that discriminate
  29 between speech and music. Neural net
  30 \glspl{HMM}.\cite{berenzweig_locating_2001}.
  31
  32 In 2014 Dzhambazov et al.\ applied state of the art segmentation methods to
  33 polyphonic turkish music, this might be interesting to use for heavy metal.
  34 They mention Fujihara(2011) to have a similar \gls{FA} system. This method uses
  35 phone level segmentation, first 12 \gls{MFCC}s. They first do vocal/non-vocal
  36 detection, then melody extraction, then alignment. They compare results with
  37 Mesaros \& Virtanen, 2008.
  38
  39 t\cite{dzhambazov_automatic_2014}
  40 t\cite{dzhambazov_automatic_2016}
  41 t\cite{fujihara_automatic_2006}
  42 t\cite{fujihara_lyricsynchronizer:_2011}
  43 t\cite{fujihara_three_2008}
  44 t\cite{mauch_integrating_2012}
  45 t\cite{mesaros_adaptation_2009}
  46 t\cite{mesaros_automatic_2008}
  47 t\cite{mesaros_automatic_2010}
  48 t\cite{muller_multimodal_2012}
  49 t\cite{pedone_phoneme-level_2011}
  50 t\cite{yang_machine_2012}
  51
  52 \bibliographystyle{ieeetr}
  53 \bibliography{asr}
  54 \end{document}