aufteilung, schlechte bilder.

icmpc2018
Denis Knauf 2018-07-17 22:42:44 +02:00
parent 12c985471a
commit d8b3950111
23 changed files with 268 additions and 222 deletions

144
brushed-metal.dark.svg Normal file
View File

@ -0,0 +1,144 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!-- Created with Inkscape (http://www.inkscape.org/) -->
<svg
xmlns:osb="http://www.openswatchbook.org/uri/2009/osb"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:cc="http://creativecommons.org/ns#"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:svg="http://www.w3.org/2000/svg"
xmlns="http://www.w3.org/2000/svg"
xmlns:xlink="http://www.w3.org/1999/xlink"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
width="841mm"
height="1189mm"
viewBox="0 0 2979.9213 4212.9921"
id="svg2"
version="1.1"
inkscape:version="0.91 r13725"
sodipodi:docname="brushed-metal.dark.svg">
<defs
id="defs4">
<linearGradient
inkscape:collect="always"
id="linearGradient5938">
<stop
style="stop-color:#000000;stop-opacity:1;"
offset="0"
id="stop5940" />
<stop
style="stop-color:#000000;stop-opacity:0;"
offset="1"
id="stop5942" />
</linearGradient>
<linearGradient
inkscape:collect="always"
id="linearGradient4468"
osb:paint="gradient">
<stop
style="stop-color:#252220;stop-opacity:1"
offset="0"
id="stop4470" />
<stop
style="stop-color:#252220;stop-opacity:0;"
offset="1"
id="stop4472" />
</linearGradient>
<filter
inkscape:label="Film Grain"
inkscape:menu="Image Effects"
inkscape:menu-tooltip="Adds a small scale graininess"
style="color-interpolation-filters:sRGB;"
id="filter4686">
<feTurbulence
type="fractalNoise"
numOctaves="3"
baseFrequency="0.002 1"
seed="0"
result="result0"
id="feTurbulence4688" />
<feColorMatrix
result="result4"
values="0"
type="saturate"
id="feColorMatrix4690" />
<feComposite
in="SourceGraphic"
in2="result4"
operator="arithmetic"
k1="0.40000000000000002"
k2="0.69999999999999996"
k3="0.14999999999999999"
result="result2"
id="feComposite4692"
k4="0.050000000000000003" />
<feBlend
result="result5"
mode="normal"
in="result2"
in2="SourceGraphic"
id="feBlend4694" />
<feComposite
in="result5"
in2="SourceGraphic"
operator="in"
result="result3"
id="feComposite4696" />
</filter>
<linearGradient
inkscape:collect="always"
xlink:href="#linearGradient5938"
id="linearGradient5944"
x1="1015.5103"
y1="-943.53088"
x2="2004.254"
y2="-945.79633"
gradientUnits="userSpaceOnUse" />
</defs>
<sodipodi:namedview
id="base"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageopacity="0.0"
inkscape:pageshadow="2"
inkscape:zoom="0.7"
inkscape:cx="1497.8194"
inkscape:cy="2020.9878"
inkscape:document-units="px"
inkscape:current-layer="layer1"
showgrid="false"
objecttolerance="20"
inkscape:window-width="1366"
inkscape:window-height="729"
inkscape:window-x="0"
inkscape:window-y="23"
inkscape:window-maximized="1"
inkscape:object-paths="false" />
<metadata
id="metadata7">
<rdf:RDF>
<cc:Work
rdf:about="">
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
<dc:title></dc:title>
</cc:Work>
</rdf:RDF>
</metadata>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1"
transform="translate(0,3160.6299)">
<rect
style="fill-opacity:1;fill-rule:nonzero;stroke:none;stroke-width:2;stroke-linecap:round;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;filter:url(#filter4686);fill:url(#linearGradient5944)"
id="rect4136"
width="3054.7012"
height="4283.0469"
x="-16.162441"
y="-3182.1973" />
</g>
</svg>

After

Width:  |  Height:  |  Size: 4.1 KiB

BIN
files/LastFM.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 17 KiB

BIN
files/blunt_chromagram.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 21 KiB

BIN
files/blunt_dyndist.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 11 KiB

BIN
files/blunt_envelope.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 13 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 25 KiB

BIN
files/decap_chromagram.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 22 KiB

BIN
files/decap_dyndist.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 9.4 KiB

BIN
files/decap_envelope.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 13 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 121 KiB

BIN
files/icmpc15_logo.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

BIN
files/icmpc15_logo.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 13 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.8 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 95 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 103 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 94 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 92 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 92 KiB

BIN
files/univie_logo.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 28 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 426 KiB

View File

@ -1,5 +1,4 @@
- require "base64"
~ "\xEF\xBB\xBF"
- def quellen opts
- etc = opts.key? :etc
- if etc
@ -14,6 +13,7 @@
- mime_type = IO.popen(["file", "--brief", "--mime-type", file], in: :close, err: :close) { |io| io.read.chomp }
- content = Base64.urlsafe_encode64 File.read( file)
- "data:#{mime_type};base64,#{content}"
~ "\xEF\xBB\xBF"
!!! 5
%html(lang='en')
%head
@ -39,8 +39,8 @@
%body
%header(style="")
%figure.logos(style="margin-top:0.3cm")<>
%img#tagungs-logo(style="float:right" src="files/icmpc15_logo.jpg")
%img#uni-logo(src="files/univie_logo.png")
%img#tagungs-logo(style="float:right" src="files/icmpc15_logo.png")
%img#uni-logo(src="files/Uni_Logo_2016_ausschnitt.gif")
-#%div(style="font-size:0.8em;margin-top:1.31cm")
44. Jahrestagung für Akustik
%br<>
@ -65,10 +65,19 @@
%main
#column1_1
%section#heavy_features
%section#hardness
%h1 Hardness
%p
<q>Hardness</q> is often considered a distinctive feature of (heavy)
metal music, as well as in genres like hardcore techno or <q>Neue
Deutsche Härte</q>.
In a previous investigation the concept of <q>hardness</q> in music
was examined in terms of its acoustic correlates and suitability as
a descriptor for music #{quellen 'Czedik-Eysenberg et al.' => 2017}.
:markdown
Sound Features
==============
--------------
Considering Bonferroni correction, 65 significant feature
correlations were found for the concept of <q>hardness</q>.
@ -81,24 +90,25 @@
%li
percussive energy / rhythmic density
%figure
%img(style="width:50%" src="files/sonagramm_blunt_log.png")
%img(style="width:50%" src="files/sonagramm_decap_log.png")
%img.fifty(src="files/sonagramm_blunt_log.png")
%img.fifty(src="files/sonagramm_decap_log.png")
%li
dynamic distribution
%figure
%img(style="width:50%" src="files/blunt_envelope.png")
%img(style="width:50%" src="files/decap_envelope.png")
%img.fifty(src="files/blunt_envelope.png")
%img.fifty(src="files/decap_envelope.png")
%figure
%img(style="width:50%" src="files/blunt_dyndist.png")
%img(style="width:50%" src="files/decap_dyndist.png")
%img.fifty(src="files/blunt_dyndist.png")
%img.fifty(src="files/decap_dyndist.png")
%li
melodic content / harmonic entropy
%figure
%img(style="width:50%" src="files/blunt_chromagram.png")
%img(style="width:50%" src="files/decap_chromagram.png")
%section#heavy_model
%h1 Model
%img.fifty(src="files/blunt_chromagram.png")
%img.fifty(src="files/decap_chromagram.png")
:markdown
Model
-----
Sequential feature selection
* set of 5 features
@ -111,12 +121,12 @@
r | 0.900
%figure
%img(src="scatter_hardness_model5.png")
%section#heavy_rater_agreement
:markdown
Rater Agreement
===============
---------------
Intraclass Correlation Coefficient (Two-Way Model, Consistency): <b>0.653</b>
.clear
#column1_2
-#%section#aims
@ -132,110 +142,33 @@
%h1 Method
%figure.right(style="width:50%")
%img(src="files/LastFM.png")
:markdown
%p
Based on last.fm listener statistics, 150 pieces of music were selected
from 10 different subgenres of metal, techno, gothic and pop music.
%p
In an online listening test, 40 participants were asked to rate the
refrain of each example in terms of <q>hardness</q> and <q>darkness</q>.
These ratings served as a ground truth for examining the two
concepts using a machine learning approach:
%figure.right(style="width:50%")
%img(src="files/diagramm_vorgang_english.png")
%p
Taking into account 230 features describing spectral distribution,
temporal and dynamic properties, relevant dimensions were
investigated and combined into models.
Predictors were trained using five-fold cross-validation.
%figure.right(style="width:50%")
%img(src="files/einhorn/diagramm_vorgang_english.png")
%section#data
%h1 Data
%figure.right(style="width:50%")
.clear
%h2 Data
%figure
%img(src="files/scatter_hard_dark_dashedline_2017-09-05.png")
%section#hardness
%h1 Hardness
%p
<q>Hardness</q> is often considered a distinctive feature of (heavy)
metal music, as well as in genres like hardcore techno or <q>Neue
Deutsche Härte</q>.
In a previous investigation the concept of <q>hardness</q> in music
was examined in terms of its acoustic correlates and suitability as
a descriptor for music #{quellen 'Czedik-Eysenberg et al.' => 2017}.
#column1_3
%section#darkness
%h1 Darkness
%p
Certain kinds of music are sometimes described as <q>dark</q> in a
metaphorical sense, especially in genres like gothic or doom metal.
According to musical adjective classifications <q>dark</q> is part
of the same cluster as <q>gloomy</q>, <q>sad</q> or
<q>depressing</q> #{quellen Hevner: 1936}, which was later adopted in
computational musical affect detection
#{quellen 'Li & Oghihara' => 2003}.
This would suggest the
relevance of sound attributes that correspond with the expression
of sadness, e.g. lower pitch, small pitch movement and <q>dark</q>
timbre #{quellen Huron: 2008}. In timbre research <q>brightness</q>
is often considered one of the central perceptual axes
#{quellen Grey: 1975, 'Siddiq et al.' => 2014}, which raises the
question if <q>darkness</q> in music is also reflected as the
inverse of this timbral <q>brightness</q> concept.
%section#darkness_features
:markdown
Sound Features
==============
Considering Bonferroni correction, 35 significant feature
correlations were found for the <q>darkness</q> ratings.
While a suspected negative correlation with **timbral
<q>brightness</q>** cannot be confirmed, <q>darkness</q> appears to
be associated with a high **spectral complexity** and harmonic
traits like **major or minor mode**.
%figure
%img(src="files/scatter_spectral_centroid_essentia_darkness.png")
:markdown
Correlations between darkness rating and measures for brightness:
Feature | r | p
-----------------------|--------|----------
Spectral centroid | 0.3340 | &lt;0.01
High frequency content | 0.1526 | 0.0631
%figure
%img(src="files/violin_keyEdma_darkMean_blaugelb.png")
%p
Musical excerpts in minor mode were significantly rated as
<q>harder</q> than those in major mode. (<nobr>p &lt; 0.01</nobr>
according to t-test)
%section#darkness_model
%h1 Model
%figure
%img(src="files/scatter_darkness_model8.png")
:markdown
Sequential feature selection:
* combination of 8 features
* predictive linear regression model
RMSE| 0.81
R-Squared| 0.60
MSE| 0.65
MAE| 0.64
r| 0.7978
%section#darkness_rater_agreement
:markdown
Rater Agreement
===============
Intraclass Correlation Coefficient (Two-Way Model, Consistency):
**0.498**
%footer
.clear
%section#further_resultes_conclusion
%h1 Further Results &amp; Conclusions
%figure.fifty
%img.right(src="files/predictionTree_genreAgg2.png")
%img.right(src="files/confusionMatrix_simpleTree_genreAgg2.png")
:markdown
Further Results &amp; Conclusions
=================================
Comparison
----------
@ -262,8 +195,77 @@
E.g. a simple tree can be constructed for classification into broad
genre categories (Pop, Techno, Metal, Gothic) with an accuracy of
74%.
%img(src="files/predictionTree_genreAgg2.png")
%img(src="files/confusionMatrix_simpleTree_genreAgg2.png")
.clear
#column1_3
%section#darkness
%h1 Darkness
%p
Certain kinds of music are sometimes described as <q>dark</q> in a
metaphorical sense, especially in genres like gothic or doom metal.
According to musical adjective classifications <q>dark</q> is part
of the same cluster as <q>gloomy</q>, <q>sad</q> or
<q>depressing</q> #{quellen Hevner: 1936}, which was later adopted in
computational musical affect detection
#{quellen 'Li & Oghihara' => 2003}.
This would suggest the
relevance of sound attributes that correspond with the expression
of sadness, e.g. lower pitch, small pitch movement and <q>dark</q>
timbre #{quellen Huron: 2008}. In timbre research <q>brightness</q>
is often considered one of the central perceptual axes
#{quellen Grey: 1975, 'Siddiq et al.' => 2014}, which raises the
question if <q>darkness</q> in music is also reflected as the
inverse of this timbral <q>brightness</q> concept.
:markdown
Sound Features
--------------
Considering Bonferroni correction, 35 significant feature
correlations were found for the <q>darkness</q> ratings.
While a suspected negative correlation with **timbral
<q>brightness</q>** cannot be confirmed, <q>darkness</q> appears to
be associated with a high **spectral complexity** and harmonic
traits like **major or minor mode**.
%figure.fifty
%img(src="files/scatter_spectral_centroid_essentia_darkness.png")
:markdown
Correlations between darkness rating and measures for brightness:
Feature | r | p
-----------------------|--------|----------
Spectral centroid | 0.3340 | &lt;0.01
High frequency content | 0.1526 | 0.0631
%figure.fifty
%img(src="files/violin_keyEdma_darkMean_blaugelb.png")
%p
Musical excerpts in minor mode were significantly rated as
<q>harder</q> than those in major mode. (<nobr>p &lt; 0.01</nobr>
according to t-test)
%h2 Model
%figure.fifty
%img(src="files/scatter_darkness_model8.png")
:markdown
Sequential feature selection:
* combination of 8 features
* predictive linear regression model
RMSE| 0.81
R-Squared| 0.60
MSE| 0.65
MAE| 0.64
r| 0.7978
:markdown
Rater Agreement
---------------
Intraclass Correlation Coefficient (Two-Way Model, Consistency):
**0.498**
.clear
%footer
%section#conclusion
:markdown
Conclusion
@ -274,111 +276,6 @@
sound characteristics associated with these concepts, they can be
used for analyzing and indexing music collections and e.g. in a
decision tree for automatic genre prediction.
-#%section#ergebnisse1(style="height:96.35cm")
%h1 4. Ergebnisse
%figure.right(style="width:70%")
%img(alt='Verwelkter Mohn' src='files/violin_genre_darkMean.svg')
%p
Es zeigt sich ein Bezug zwischen dem Genre und der
durchschnittlichen Düsterkeitsbewertung der jeweiligen Stimuli.
%figure.right(style="width:35%")
%img(alt='Ernstes Indigo' src='files/scatter_spectral_centroid_essentia_darkness.svg')
%p
Eine Antiproportionalität zu klangfarblicher <q>Helligkeit</q> lässt
sich (mit der vorliegenden Messmethode) nicht nachweisen. Es liegt
im Gegenteil sogar eine leicht positive Korrelation vor
womöglich u.a. bedingt durch erhöhte dissonante Klanganteile im
Hochfrequenzbereich (z.B. Schlagzeugvorkommen). Werden die
perkussiven Signalanteile zuvor ausgefiltert, verringert sich
dieser Effekt bereits deutlich.
%figure.nobrtd(style="width:24em")
:markdown
Merkmal|r|p
---|---|---
Spectral Centroid|0,3340|&lt; 0,0001
Hochfrequenzanteil (> 1500 Hz)|0,1526|0,0631
Spectral Centroid (harmonischer Teil)|0,2094|0,0101
Hochfrequenzanteil (harmonischer Teil)|0,1270|0,1215
{:.merkmale}
%figcaption
Korrelation der durchschnittlichen Düsterkeits<wbr/>bewertung mit Maßen
für klangfarbliche Helligkeit.
.clear
%figure.left(style="width:41.1%")
%img(alt='Trauriges Purpur' src='files/violin_keyEdma_darkMean_blaugelb.svg')
%figure
%figure.right(style="width:12em")
%img(alt="lilien grau" src="files/meanspectra_10khz_600dpi.png")
%figure.right
:markdown
Merkmal|r|p
---|---|---
RMS Gammatone 1|- 0,3989|&lt; 0,0001
RMS Gammatone 4|- 0,3427|&lt; 0,0001
RMS Gammatone 5|- 0,3126|0,0001
{:.merkmale}
%p(style="clear:right")
Zwischen den 30 am düstersten bzw. am wenigsten düster bewerteten
Klangbeispielen zeigen sich charakteristische Unterschiede in der spektralen
Verteilung (insbesondere im Bereich der Gammatone-Filterbank-Bänder 1, 4 und 5).
%p(style="clear:right")
Ein deutlicher Zusammenhang zeigt sich mit der Tonart der
jeweiligen Ausschnitte: Moll-Beispiele wurden im Durchschnitt als
düsterer bewertet als Stücke in Dur-Tonarten (<nobr>p &lt; 0.0001</nobr> laut t-Test).
%p(style="clear:right")
Teilweise eher statische Tonchroma-Veränderungen im Fall der als
düster bewerteten Beispiele könnten die Theorie geringere
Tonhöhenbewegungen in Zusammenhang mit einem Ausdruck von Trauer
bestätigen (siehe z.B. Chromagramm <q><nobr>Sunn 0)))</nobr></q>).
%figure.right(style="width:58.2%")
%img(style="width:49%" alt='Schrumpeliges Gelb' src='files/chromagramm_sunn.svg')
%img(style="width:49%" alt='Vergängliches Weiß' src='files/chromagramm_abba.svg')
%p(style="clear:left;max-width: 50%")
Der stärkste Zusammenhang lässt sich zur Spectral Complexity
feststellen, welche die Komplexität des Signals in Bezug auf seine
Frequenzkomponenten anhand der Anzahl spektraler Peaks im Bereich
zwischen 100 Hz und 5 kHz beschreibt. Dies ist interessant mit den
Ergebnissen von #{quellen 'Laurier et al.' => 2010} in Bezug zu setzen,
welche beobachteten, dass <q>entspannte</q> (<q>relaxed</q>) Stücke eine
niedrigere spektrale Komplexität aufweisen, <q>fröhliche</q> (<q>happy</q>)
Stücke jedoch eine leicht höhere spektrale Komplexität als
<q>nicht fröhliche</q>.
%figure.left(style="width:59.83%;position:relative")
%img(alt='Totes Grün' src='files/scatter_model8_mit_beschriftung_gross.svg')
%img(alt="Farbiges Beispiel" style="width:5cm;opacity:0.7;position:absolute;top:0;left:3cm" src="files/bat.png")
%p(style="clear:right")
Nach sequentieller Merkmalsauswahl wurden 8 Signaldeskriptoren zur
Bildung eines Modells zu Rate gezogen:
:markdown
Merkmal|r|p
----|----|----
Spectral Complexity (mean)| 0,6224| &lt; 0,0001
HPCP Entropy (mean)| 0,5355| &lt; 0,0001
Dynamic Complexity| - 0,4855| &lt; 0,0001
Onset Rate| - 0,4837| &lt; 0,0001
Pitch Salience| 0,4835| &lt; 0,0001
MFCC 3 (mean)| 0,4657| &lt; 0,0001
Spectral Centroid (mean)| 0,3340| &lt; 0,0001
RMS Energy Gammatone 4| - 0,3427| &lt; 0,0001
{:.merkmale}
%p
Anhand dieser wurde unter 5-facher Kreuzvalidierung ein lineares
Regressionsmodell zur Abschätzung der Düsterkeitsbewertung erstellt.
:markdown
Merkmal|Wert
----|----
Root-mean-squared error (RMSE)|0,81<span class="hidden">00</span>
Bestimmtheitsmaß (R<sup>2</sup>)|0,60<span class="hidden">00</span>
Mean Squared Error (MSE)|0,65<span class="hidden">00</span>
Mean Average Error (MAE)|0,64<span class="hidden">00</span>
Korrelation (insgesamt)|0,7978
{:.merkmale}
%div(style="clear:left")
.clear
%section#references
-#(style="width:44.5%;display:inline-block;float:right")
@ -389,8 +286,7 @@
%span.year 2017
%span.title <q>Hardness</q> as a semantic audio descriptor for music using automatic feature extraction
%span.herausgeber Gesellschaft für Informatik, Bonn
%span.link
%a(href="https://doi.org/10.18420/in2017_06") https://doi.org/10.18420/in2017_06
%span.link= link 'https://doi.org/10.18420/in2017_06'
%li
%span.author Grey, J.M.
%span.year 1975

View File

@ -143,8 +143,7 @@ footer {
body {
margin: 0;
background: url(files/marble_black.png); //url(brushed-metal.new.svg);
background: url(brushed-metal.pink.svg);
background: url(brushed-metal.dark.svg), url(files/marble_black.png), #252220;
color: #565655;
font-family: "Cardo";
}
@ -167,19 +166,23 @@ section {
font-size: 0.95em;
//text-align: justify;
&:first-child {
&:first-child + * {
margin-top: 1em;
}
//&:first-child {
&, &::before {
border-top-right-radius: 2rem;
border-top-left-radius: 2rem;
//margin-top: 0;
}
}
&:last-child {
//}
//&:last-child {
&, &::before {
border-bottom-right-radius: 0.5rem;
border-bottom-left-radius: 0.5rem;
}
}
//}
&::before {
z-index: -1;
@ -196,6 +199,9 @@ section {
-webkit-print-color-adjust: exact;
-webkit-filter: opacity(1);
}
&[header-background]::before {
background: linear-gradient( rgba(205, 106, 81, 0.8) 2.2rem, rgba(256, 256, 256, 0.8) 2.3rem );
}
h1:first-child {
//border-bottom: 0.3rem solid black