From: Mart Lubbers <mart@martlubbers.net>
Date: Mon, 6 Mar 2017 19:30:03 +0000 (+0100)
Subject: update, add proposal
X-Git-Url: https://git.martlubbers.net/?a=commitdiff_plain;h=1fb9c069bb68760071a96e201462e85680939863;p=asr1617.git

update, add proposal
---

diff --git a/Makefile b/Makefile
index 8f3a88a..ea2399a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-DOCS:=asr
+DOCS:=asr proposal
 GREP?=grep
 LATEX?=pdflatex
 BIBTEX?=bibtex
diff --git a/asr.tex b/asr.tex
index 42af838..87aae4e 100644
--- a/asr.tex
+++ b/asr.tex
@@ -52,6 +52,17 @@ t\cite{muller_multimodal_2012}
 t\cite{pedone_phoneme-level_2011}
 t\cite{yang_machine_2012}
 
+
+%Introduction, leading to a clearly defined research question
+%Literature overview / related work
+%Methodology
+%Experiment(s) (set-up, data, results, discussion)
+%Discussion section
+%Conclusion section
+%Acknowledgements
+%Statement on authors' contributions
+%(Appendices)
+
 \bibliographystyle{ieeetr}
 \bibliography{asr}
 \end{document}
diff --git a/proposal.pre b/proposal.pre
new file mode 100644
index 0000000..5f67969
--- /dev/null
+++ b/proposal.pre
@@ -0,0 +1,22 @@
+\documentclass[a4paper]{article}
+
+\usepackage[british]{babel}
+
+\usepackage{geometry}                % Papersize
+\usepackage{hyperref}                % Hyperlinks
+
+\urlstyle{same}
+\hypersetup{%
+	pdftitle={},
+	pdfauthor={Mart Lubbers},
+	pdfsubject={},
+	pdfcreator={Mart Lubbers},
+	pdfproducer={Mart Lubbers},
+	pdfkeywords={},
+	hidelinks=true
+}
+
+\title{(Automatic) Speech Recognition\\{\large Proposal}}
+\author{Mart Lubbers\\
+	{\small\href{mailto:mart@martlubbers.net}{mart@martlubbers.net}}}
+\date{\today}
diff --git a/proposal.tex b/proposal.tex
new file mode 100644
index 0000000..a5125d0
--- /dev/null
+++ b/proposal.tex
@@ -0,0 +1,25 @@
+%&proposal
+\begin{document}
+\maketitle
+
+My proposed research consists of two questions of which the thesis will answer
+at least one.
+
+The first topic is singing voice detection. Singing voice detection has been
+done on numerous amounts of musical styles ranging from unconventional styles
+like Beijing opera to conventional pop music. Moreover, the problem has been
+tackled using myriads of different approaches such as HMMs with different
+acoustic model types but also machine learned feature sets. I would like to
+explore how HMM based techniques perform on extreme heavy metal styles to see
+how well it can detect growling and how classifier might be adapted to perform
+better.
+
+Singing voice detection is often used as a preprocessing step for song lyrics
+forced alignment. If the time permits I would like to explore forced alignment
+using existing phone models on extreme heavy metal styles. Features probably
+need to be changed to improve performance since growling is very different from
+regular singing and speaking.
+
+The data for this will be coming from my personal collection audio CDs.
+
+\end{document}