final
Denis Knauf
parent
2e7ff4ce30
commit
7c436704cb
|
|
@ -7,4 +7,5 @@ fonts/*.map
|
|||
style.css
|
||||
*.swp
|
||||
/.bundle
|
||||
/files/einhorn
|
||||
/vendor/bundle
|
||||
|
|
|
|||
|
|
@ -24,11 +24,11 @@
|
|||
inkscape:collect="always"
|
||||
id="linearGradient5938">
|
||||
<stop
|
||||
style="stop-color:#000000;stop-opacity:1;"
|
||||
style="stop-color:#6d635e;stop-opacity:1;"
|
||||
offset="0"
|
||||
id="stop5940" />
|
||||
<stop
|
||||
style="stop-color:#000000;stop-opacity:0;"
|
||||
style="stop-color:#6d635e;stop-opacity:0;"
|
||||
offset="1"
|
||||
id="stop5942" />
|
||||
</linearGradient>
|
||||
|
|
@ -37,11 +37,11 @@
|
|||
id="linearGradient4468"
|
||||
osb:paint="gradient">
|
||||
<stop
|
||||
style="stop-color:#252220;stop-opacity:1"
|
||||
style="stop-color:#6d635e;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop4470" />
|
||||
<stop
|
||||
style="stop-color:#252220;stop-opacity:0;"
|
||||
style="stop-color:#6d635e;stop-opacity:0;"
|
||||
offset="1"
|
||||
id="stop4472" />
|
||||
</linearGradient>
|
||||
|
|
|
|||
|
Before Width: | Height: | Size: 4.1 KiB After Width: | Height: | Size: 4.1 KiB |
|
Before Width: | Height: | Size: 17 KiB After Width: | Height: | Size: 17 KiB |
|
Before Width: | Height: | Size: 18 KiB After Width: | Height: | Size: 18 KiB |
|
Before Width: | Height: | Size: 7.3 KiB After Width: | Height: | Size: 7.3 KiB |
|
Before Width: | Height: | Size: 8.9 KiB After Width: | Height: | Size: 8.9 KiB |
|
Before Width: | Height: | Size: 25 KiB After Width: | Height: | Size: 25 KiB |
|
Before Width: | Height: | Size: 19 KiB After Width: | Height: | Size: 19 KiB |
|
Before Width: | Height: | Size: 5.7 KiB After Width: | Height: | Size: 5.7 KiB |
|
Before Width: | Height: | Size: 9.2 KiB After Width: | Height: | Size: 9.2 KiB |
|
Before Width: | Height: | Size: 93 KiB After Width: | Height: | Size: 93 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 102 KiB |
|
Before Width: | Height: | Size: 7.6 KiB After Width: | Height: | Size: 7.6 KiB |
|
|
@ -0,0 +1,94 @@
|
|||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN" "http://www.w3.org/TR/2001/PR-SVG-20010719/DTD/svg10.dtd">
|
||||
<svg width="20cm" height="11cm" viewBox="-440 -300 381 216" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
|
||||
<g id="Hintergrund">
|
||||
<g>
|
||||
<rect style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x="-306" y="-299" width="106" height="40" rx="0" ry="0"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-253" y="-275.1">
|
||||
<tspan x="-253" y="-275.1">darkness</tspan>
|
||||
</text>
|
||||
</g>
|
||||
<g>
|
||||
<line style="fill: none; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x1="-249.998" y1="-258" x2="-293.895" y2="-221.155"/>
|
||||
<polygon style="fill: #000000; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" points="-297.11,-224.984 -301.555,-214.726 -290.681,-217.325 "/>
|
||||
</g>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-333.998" y="-234">
|
||||
<tspan x="-333.998" y="-234">< 3.573</tspan>
|
||||
<tspan x="-333.998" y="-218"></tspan>
|
||||
</text>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-299" y="-244">
|
||||
<tspan x="-299" y="-244"></tspan>
|
||||
</text>
|
||||
<g>
|
||||
<line style="fill: none; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x1="-248.998" y1="-258" x2="-205.945" y2="-222.234"/>
|
||||
<polygon style="fill: #000000; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" points="-209.14,-218.388 -198.253,-215.843 -202.75,-226.08 "/>
|
||||
</g>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-214.998" y="-235">
|
||||
<tspan x="-214.998" y="-235">>= 3.573</tspan>
|
||||
</text>
|
||||
<g>
|
||||
<rect style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x="-380.2" y="-213.2" width="106" height="40" rx="0" ry="0"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-327.2" y="-189.3">
|
||||
<tspan x="-327.2" y="-189.3">hardness</tspan>
|
||||
</text>
|
||||
</g>
|
||||
<g>
|
||||
<rect style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x="-225.2" y="-214.2" width="106" height="40" rx="0" ry="0"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-172.2" y="-190.3">
|
||||
<tspan x="-172.2" y="-190.3">hardness</tspan>
|
||||
</text>
|
||||
</g>
|
||||
<g>
|
||||
<line style="fill: none; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x1="-327.2" y1="-173.2" x2="-366.891" y2="-138.903"/>
|
||||
<polygon style="fill: #000000; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" points="-370.16,-142.687 -374.458,-132.365 -363.622,-135.12 "/>
|
||||
</g>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-407" y="-149">
|
||||
<tspan x="-407" y="-149">< 3.294</tspan>
|
||||
</text>
|
||||
<g>
|
||||
<line style="fill: none; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x1="-327.2" y1="-173.2" x2="-314.226" y2="-141.38"/>
|
||||
<polygon style="fill: #000000; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" points="-318.856,-139.493 -310.451,-132.12 -309.596,-143.268 "/>
|
||||
</g>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-312.998" y="-149">
|
||||
<tspan x="-312.998" y="-149">>= 3.294</tspan>
|
||||
</text>
|
||||
<g>
|
||||
<line style="fill: none; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x1="-172.2" y1="-174.2" x2="-185.641" y2="-141.358"/>
|
||||
<polygon style="fill: #000000; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" points="-190.268,-143.252 -189.428,-132.103 -181.013,-139.464 "/>
|
||||
</g>
|
||||
<g>
|
||||
<line style="fill: none; stroke-opacity: 1; stroke-width: 2; stroke: #000000" x1="-172.2" y1="-174.2" x2="-132.695" y2="-138.478"/>
|
||||
<polygon style="fill: #000000; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" points="-136.048,-134.769 -125.277,-131.771 -129.341,-142.186 "/>
|
||||
</g>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-235.998" y="-149">
|
||||
<tspan x="-235.998" y="-149">< 4.632</tspan>
|
||||
</text>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:start;font-family:sans-serif;font-style:normal;font-weight:normal" x="-138.998" y="-149">
|
||||
<tspan x="-138.998" y="-149">>= 4.632</tspan>
|
||||
</text>
|
||||
<g>
|
||||
<path style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" d="M -425.831 -131 L -377.165,-131 C -370.445,-131 -364.998,-121.15 -364.998,-109 C -364.998,-96.8497 -370.445,-87 -377.165,-87 L -425.831,-87 C -432.551,-87 -437.998,-96.8497 -437.998,-109 C -437.998,-121.15 -432.551,-131 -425.831,-131z"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-401.498" y="-105">
|
||||
<tspan x="-401.498" y="-105">Pop</tspan>
|
||||
</text>
|
||||
</g>
|
||||
<g>
|
||||
<path style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" d="M -326.023 -130.2 L -275.373,-130.2 C -268.38,-130.2 -262.71,-120.35 -262.71,-108.2 C -262.71,-96.0497 -268.38,-86.2 -275.373,-86.2 L -326.023,-86.2 C -333.016,-86.2 -338.685,-96.0497 -338.685,-108.2 C -338.685,-120.35 -333.016,-130.2 -326.023,-130.2z"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-300.698" y="-104.2">
|
||||
<tspan x="-300.698" y="-104.2">Techno</tspan>
|
||||
</text>
|
||||
</g>
|
||||
<g>
|
||||
<path style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" d="M -224.535 -130.2 L -173.885,-130.2 C -166.892,-130.2 -161.223,-120.35 -161.223,-108.2 C -161.223,-96.0497 -166.892,-86.2 -173.885,-86.2 L -224.535,-86.2 C -231.529,-86.2 -237.198,-96.0497 -237.198,-108.2 C -237.198,-120.35 -231.529,-130.2 -224.535,-130.2z"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-199.21" y="-104.2">
|
||||
<tspan x="-199.21" y="-104.2">Gothic</tspan>
|
||||
</text>
|
||||
</g>
|
||||
<g>
|
||||
<path style="fill: #ffffff; fill-opacity: 1; stroke-opacity: 1; stroke-width: 2; stroke: #000000" fill-rule="evenodd" d="M -124.536 -130.2 L -73.8855,-130.2 C -66.8922,-130.2 -61.223,-120.35 -61.223,-108.2 C -61.223,-96.0497 -66.8922,-86.2 -73.8855,-86.2 L -124.536,-86.2 C -131.529,-86.2 -137.198,-96.0497 -137.198,-108.2 C -137.198,-120.35 -131.529,-130.2 -124.536,-130.2z"/>
|
||||
<text font-size="12.7998" style="fill: #000000; fill-opacity: 1; stroke: none;text-anchor:middle;font-family:sans-serif;font-style:normal;font-weight:normal" x="-99.2105" y="-104.2">
|
||||
<tspan x="-99.2105" y="-104.2">Metal</tspan>
|
||||
</text>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 7.9 KiB |
|
Before Width: | Height: | Size: 74 KiB After Width: | Height: | Size: 74 KiB |
|
Before Width: | Height: | Size: 80 KiB After Width: | Height: | Size: 80 KiB |
|
Before Width: | Height: | Size: 73 KiB After Width: | Height: | Size: 73 KiB |
|
Before Width: | Height: | Size: 12 KiB After Width: | Height: | Size: 12 KiB |
|
Before Width: | Height: | Size: 91 KiB After Width: | Height: | Size: 91 KiB |
|
Before Width: | Height: | Size: 91 KiB After Width: | Height: | Size: 91 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 480 KiB |
|
Before Width: | Height: | Size: 18 KiB After Width: | Height: | Size: 18 KiB |
|
Before Width: | Height: | Size: 328 KiB After Width: | Height: | Size: 328 KiB |
354
index.html.haml
354
index.html.haml
|
|
@ -19,10 +19,10 @@
|
|||
%head
|
||||
-#%meta(charset="utf-8")
|
||||
%title Decoding the sound of 'hardness' and 'darkness' as perceptual dimensions of music
|
||||
-#%link(rel="stylesheet" href="fonts/Roboto.css")
|
||||
-#%link(rel="stylesheet" href="fonts/RobotoSlab.css")
|
||||
%link(rel="stylesheet" href="fonts/Roboto.css")
|
||||
%link(rel="stylesheet" href="fonts/RobotoSlab.css")
|
||||
-#%link(rel="stylesheet" href="fonts/PT_Mono.css")
|
||||
-#%link(rel="stylesheet" href="fonts/PT_Sans.css")
|
||||
%link(rel="stylesheet" href="fonts/PT_Sans.css")
|
||||
-#%link(rel="stylesheet" href="fonts/Vollkorn.css")
|
||||
-#%link(rel="stylesheet" href="fonts/Asset.css")
|
||||
-#%link(rel="stylesheet" href="fonts/WithinDestruction.css")
|
||||
|
|
@ -39,8 +39,8 @@
|
|||
%body
|
||||
%header(style="")
|
||||
%figure.logos(style="margin-top:0.3cm")<>
|
||||
%img#tagungs-logo(style="float:right" src="files/icmpc15_logo.png")
|
||||
%img#uni-logo(src="files/Uni_Logo_2016_ausschnitt.gif")
|
||||
%img#uni-logo(src="files/univie_logo.png")
|
||||
%img#tagungs-logo(style="float:right;height:i3.5em" src="files/icmpc15_logo.png")
|
||||
-#%div(style="font-size:0.8em;margin-top:1.31cm")
|
||||
44. Jahrestagung für Akustik
|
||||
%br<>
|
||||
|
|
@ -82,56 +82,85 @@
|
|||
Considering Bonferroni correction, 65 significant feature
|
||||
correlations were found for the concept of <q>hardness</q>.
|
||||
|
||||
The characterizing attributes of <q>hardness</q> include high
|
||||
tempo and sound density, less focus on clear melodic lines than
|
||||
noise-like sounds and especially the occurrence of strong percussive
|
||||
The characterizing attributes of <q>hardness</q> include **high
|
||||
tempo** and **sound density**, less focus on clear melodic lines than
|
||||
**noise-like** sounds and especially the occurrence of strong **percussive**
|
||||
components.
|
||||
%ol
|
||||
%li
|
||||
percussive energy / rhythmic density
|
||||
%figure
|
||||
%img.fifty(src="files/sonagramm_blunt_log.png")
|
||||
%img.fifty(src="files/sonagramm_decap_log.png")
|
||||
%p percussive energy / rhythmic density
|
||||
%figure.pfifty
|
||||
%figcaption Spectrogram <q>James Blunt - You're Beautiful</q>
|
||||
%img(src="files/sonagramm_blunt_log.png")
|
||||
%figure.pfifty
|
||||
%figcaption Spectrogram <q>Decapitated - The Fury</q>
|
||||
%img(src="files/sonagramm_decap_log.png")
|
||||
.clear
|
||||
%li
|
||||
dynamic distribution
|
||||
%figure
|
||||
%img.fifty(src="files/blunt_envelope.png")
|
||||
%img.fifty(src="files/decap_envelope.png")
|
||||
%figure
|
||||
%img.fifty(src="files/blunt_dyndist.png")
|
||||
%img.fifty(src="files/decap_dyndist.png")
|
||||
%p dynamic distribution
|
||||
%figure.pfifty
|
||||
%figcaption Dynamic Envelope <q>James Blunt - You're Beautiful</q>
|
||||
%img(src="files/blunt_envelope.png")
|
||||
%figure.pfifty
|
||||
%figcaption Dynamic Envelope <q>Decapitated - The Fury</q>
|
||||
%img(src="files/decap_envelope.png")
|
||||
-#%figure.pfifty
|
||||
%figcaption Dynamic distribution <q>James Blunt - You're Beautiful</q>
|
||||
%img(src="files/blunt_dyndist.png")
|
||||
-#%figure.pfifty
|
||||
%figcaption Dynamic distribution <q>Decapitated - The Fury</q>
|
||||
%img(src="files/decap_dyndist.png")
|
||||
.clear
|
||||
%li
|
||||
melodic content / harmonic entropy
|
||||
%figure
|
||||
%img.fifty(src="files/blunt_chromagram.png")
|
||||
%img.fifty(src="files/decap_chromagram.png")
|
||||
:markdown
|
||||
Model
|
||||
-----
|
||||
%p melodic content / harmonic entropy
|
||||
%figure.pfifty
|
||||
%figcaption Chromagramm <q>James Blunt - You're Beautiful</q>
|
||||
%img(src="files/blunt_chromagram.png")
|
||||
%figure.pfifty
|
||||
%figcaption Chromagram <q>Decapitated - The Fury</q>
|
||||
%img(src="files/decap_chromagram.png")
|
||||
.clear
|
||||
|
||||
Sequential feature selection
|
||||
|
||||
* set of 5 features
|
||||
* predictive linear regression model
|
||||
|
||||
RMSE | 0.64
|
||||
R-Squared | 0.80
|
||||
MSE | 0.40
|
||||
MAE | 0.49
|
||||
r | 0.900
|
||||
%figure
|
||||
%img(src="scatter_hardness_model5.png")
|
||||
-#%h2(style="margin-top:1.5em") Model
|
||||
%h2(style="margin-top:40px") Model
|
||||
%figure.fifty.left(style="width:67%;text-align:center")
|
||||
%img(src="files/scatter_hardness_model5.png")
|
||||
%div(style="display:inline-block")
|
||||
:markdown
|
||||
RMSE | R<sup>2</sup> | MSE | MAE | r
|
||||
0.64 | 0.80 | 0.40 | 0.49 | 0.90
|
||||
%p(style="text-align:center")<>
|
||||
Sequential feature selection
|
||||
%br<>
|
||||
↓
|
||||
%br<>
|
||||
set of 5 features
|
||||
%br<>
|
||||
↓
|
||||
%br<>
|
||||
<b>predictive linear regression model</b>
|
||||
-#
|
||||
RMSE | 0.64
|
||||
R<sup>2</sup> | 0.80
|
||||
MSE | 0.40
|
||||
MAE | 0.49
|
||||
r | 0.90
|
||||
.clear
|
||||
:markdown
|
||||
Rater Agreement
|
||||
---------------
|
||||
|
||||
Intraclass Correlation Coefficient (Two-Way Model, Consistency): <b>0.653</b>
|
||||
Intraclass Correlation Coefficient <nobr>(Two-Way Model, Consistency): <b>0.653</b></nobr>
|
||||
.clear
|
||||
|
||||
#column1_2
|
||||
-#%section#aims
|
||||
%section#aims
|
||||
%h1 Aims
|
||||
%p
|
||||
The semantic concepts of <q>hardness</q> and <q>darkness</q> in music are analyzed
|
||||
in terms of their corresponding sound attributes. Based on listening test data,
|
||||
predictive models for both dimensions are created and compared.
|
||||
-#%p
|
||||
Based on computationally obtainable signal features, the creation
|
||||
of models for the perceptual concepts of <q>hardness</q> and
|
||||
<q>darkness</q> in music is aimed for. Furthermore it shall be
|
||||
|
|
@ -140,7 +169,7 @@
|
|||
these dimensions.
|
||||
%section#method
|
||||
%h1 Method
|
||||
%figure.right(style="width:50%")
|
||||
%figure.right(style="width:12%;height:2em;margin: 0.5em 0.5em 0.5em 1.5em")
|
||||
%img(src="files/LastFM.png")
|
||||
%p
|
||||
Based on last.fm listener statistics, 150 pieces of music were selected
|
||||
|
|
@ -151,7 +180,8 @@
|
|||
These ratings served as a ground truth for examining the two
|
||||
concepts using a machine learning approach:
|
||||
|
||||
%figure.right(style="width:50%")
|
||||
%figure.right
|
||||
//(style="width:50%")
|
||||
%img(src="files/diagramm_vorgang_english.png")
|
||||
%p
|
||||
Taking into account 230 features describing spectral distribution,
|
||||
|
|
@ -159,45 +189,25 @@
|
|||
investigated and combined into models.
|
||||
Predictors were trained using five-fold cross-validation.
|
||||
.clear
|
||||
%h2 Data
|
||||
|
||||
-#.blockarrow(style="display:block;width:100%;font-size:6em;margin:0") 🠳
|
||||
%section#data(style="margin-top:2em")
|
||||
%h1 Data
|
||||
%figure
|
||||
%img(src="files/scatter_hard_dark_dashedline_2017-09-05.png")
|
||||
.blockarrow(style="top:-3.8rem;left:0;right:0") 🡇
|
||||
.blockarrow(style="bottom:9rem;left:-3rem") 🡄
|
||||
.blockarrow(style="bottom:9rem;right:-3rem") 🡆
|
||||
.clear
|
||||
%section#further_resultes_conclusion
|
||||
%h1 Further Results & Conclusions
|
||||
%figure.fifty
|
||||
%img.right(src="files/predictionTree_genreAgg2.png")
|
||||
%img.right(src="files/confusionMatrix_simpleTree_genreAgg2.png")
|
||||
:markdown
|
||||
Comparison
|
||||
----------
|
||||
|
||||
When comparing <q>darkness</q> and <q>hardness</q>, the results
|
||||
indicate that the latter concept can be more efficiently described
|
||||
and modeled by specific sound attributes:
|
||||
|
||||
* The consistency between ratings given by different raters is
|
||||
higher for <q>hardness</q> (see Intraclass Correlation
|
||||
Coefficients)
|
||||
* For the <q>hardness</q> dimension, a model can be based on a more
|
||||
compact set of features and at the same time leads to a better
|
||||
prediction rate
|
||||
|
||||
Further application
|
||||
-------------------
|
||||
|
||||
Although a considerable linear relation
|
||||
(<nobr>r = 0.65</nobr>, <nobr>p < 0.01</nobr>) is present between
|
||||
the two dimensions within the studied dataset, the concepts prove to
|
||||
be useful criteria for distinguishing music examples from different
|
||||
genres.
|
||||
|
||||
E.g. a simple tree can be constructed for classification into broad
|
||||
genre categories (Pop, Techno, Metal, Gothic) with an accuracy of
|
||||
74%.
|
||||
%div(style="margin-top:1em;margin-bottom:-1em")
|
||||
%div(style="width:40%;display:inline-block;float:left;text-align:center")
|
||||
-#%img(src="files/hammer-306313_960_720.png" style="height:5em")
|
||||
%img(src="files/thor-hammer3.png" style="height:5em")
|
||||
.blockarrow(style="display:block;width:100%;font-size:7.5rem;margin:0;margin-top:-1.3rem") 🡇
|
||||
%div(style="width:40%;display:inline-block;float:right;text-align:center")
|
||||
%img(src="files/Candle.png" style="height:5em")
|
||||
.clear
|
||||
|
||||
|
||||
#column1_3
|
||||
%section#darkness
|
||||
%h1 Darkness
|
||||
|
|
@ -225,92 +235,144 @@
|
|||
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
|
||||
<q>brightness</q>** can **not** be confirmed, <q>darkness</q> appears to
|
||||
be associated with a high **spectral complexity** and harmonic
|
||||
traits like **major or minor mode**.
|
||||
%figure.fifty
|
||||
%figure.fifty.left
|
||||
%img(src="files/scatter_spectral_centroid_essentia_darkness.png")
|
||||
:markdown
|
||||
Correlations between darkness rating and measures for brightness:
|
||||
%div(style="height:1em")
|
||||
%p No evidence for negative correlations between darkness rating and measures for brightness:
|
||||
|
||||
Feature | r | p
|
||||
-----------------------|--------|----------
|
||||
Spectral centroid | 0.3340 | <0.01
|
||||
High frequency content | 0.1526 | 0.0631
|
||||
%figure.fifty
|
||||
%div(style="text-align:center")
|
||||
%div(style="display:inline-block")
|
||||
:markdown
|
||||
Feature | r | p
|
||||
-----------------------|-------|----------
|
||||
<nobr>Spectral centroid</nobr> | 0.334 | <0.01
|
||||
<nobr>High frequency content</nobr> | 0.153 | 0.063
|
||||
%figure.fifty(style="margin-top:0.4em")
|
||||
%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 < 0.01</nobr>
|
||||
according to t-test)
|
||||
%h2 Model
|
||||
%figure.fifty
|
||||
%figure.fifty.right(style="width:67%;text-align:center;margin-bottom:3px")
|
||||
%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
|
||||
%div(style="display:inline-block")
|
||||
:markdown
|
||||
RMSE | R<sup>2</sup> | MSE | MAE | r
|
||||
0.81 | 0.60 | 0.65 | 0.64 | 0.798
|
||||
%p(style="text-align:center")<>
|
||||
Sequential feature selection
|
||||
%br<>
|
||||
↓
|
||||
%br<>
|
||||
set of 8 features
|
||||
%br<>
|
||||
↓
|
||||
%br<>
|
||||
<b>predictive linear regression model</b>
|
||||
-#
|
||||
RMSE | 0.81
|
||||
R<sup>2</sup> | 0.60
|
||||
MSE | 0.65
|
||||
MAE | 0.64
|
||||
r | 0.798
|
||||
.clear
|
||||
:markdown
|
||||
Rater Agreement
|
||||
---------------
|
||||
|
||||
Intraclass Correlation Coefficient (Two-Way Model, Consistency):
|
||||
**0.498**
|
||||
Intraclass Correlation Coefficient <nobr>(Two-Way Model, Consistency):
|
||||
<b>0.498</b></nobr>
|
||||
.clear
|
||||
|
||||
%footer
|
||||
%section#conclusion
|
||||
:markdown
|
||||
Conclusion
|
||||
==========
|
||||
%footer(style="padding-top:0.2em")
|
||||
%section#further_resultes_conclusion(style="padding-bottom:0.20em")
|
||||
%h1 Further Results & Conclusions
|
||||
%div
|
||||
#column2_1
|
||||
:markdown
|
||||
Comparison
|
||||
----------
|
||||
|
||||
<q>Hardness</q> and <q>darkness</q> constitute perceptually relevant
|
||||
dimensions for a high-level description of music. By decoding the
|
||||
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.
|
||||
When comparing <q>darkness</q> and <q>hardness</q>, the results
|
||||
indicate that the latter concept can be more efficiently described
|
||||
and modeled by specific sound attributes:
|
||||
|
||||
%section#references
|
||||
-#(style="width:44.5%;display:inline-block;float:right")
|
||||
%h1 References
|
||||
%ul.literatur
|
||||
%li
|
||||
%span.author Czedik-Eysenberg, I., Knauf, D., & Reuter, C.
|
||||
%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= link 'https://doi.org/10.18420/in2017_06'
|
||||
%li
|
||||
%span.author Grey, J.M.
|
||||
%span.year 1975
|
||||
%span.title An Exploration of Musical Timbre
|
||||
%span.herausgeber Stanford University, CCRMA Report No.STAN-M-2
|
||||
%li
|
||||
%span.author Li,T., Ogihara,M.
|
||||
%span.year 2003
|
||||
%span.title Detecting emotion in music
|
||||
%nobr
|
||||
%span.herausgeber 4th ISMIR Washington & Baltimore
|
||||
%span.pages 239-240
|
||||
%li
|
||||
%span.author Huron, D.
|
||||
%span.year 2008
|
||||
%span.title A comparison of average pitch height and interval size in major-and minor-key themes
|
||||
%nobr
|
||||
%span.herausgeber Empirical Musicology Review, 3
|
||||
%span.pages 59-63
|
||||
%li
|
||||
%span.author Siddiq,S. et al.
|
||||
%span.year 2014
|
||||
%span.title Kein Raum für Klangfarben - Timbre Spaces im Vergleich
|
||||
%nobr
|
||||
%span.herausgeber 40. DAGA
|
||||
%span.pages 56-57
|
||||
.clear
|
||||
* The consistency between ratings given by different raters is
|
||||
higher for <q>hardness</q> (see Intraclass Correlation
|
||||
Coefficients)
|
||||
* For the <q>hardness</q> dimension, a model can be based on a more
|
||||
compact set of features and at the same time leads to a better
|
||||
prediction rate
|
||||
|
||||
#column2_2
|
||||
:markdown
|
||||
Further application
|
||||
-------------------
|
||||
|
||||
%figure.fifty(style="width:37%")
|
||||
%img(src="files/confusionMatrix_simpleTree_genreAgg2.png")
|
||||
:markdown
|
||||
Although a considerable linear relation
|
||||
(<nobr>r = 0.65</nobr>, <nobr>p < 0.01</nobr>) is present between
|
||||
the two dimensions within the studied dataset, the concepts prove to
|
||||
be useful criteria for distinguishing music examples from different
|
||||
genres.
|
||||
%figure.quarterly(style="clear:initial;width:28%")
|
||||
%img(src="files/predictionTree_genreAgg2.svg")
|
||||
%p
|
||||
E.g. a simple tree can be constructed for classification into broad
|
||||
genre categories (Pop, Techno, Metal, Gothic) with an accuracy of
|
||||
74 %.
|
||||
|
||||
#column2_3
|
||||
:markdown
|
||||
Conclusion
|
||||
----------
|
||||
|
||||
<q>Hardness</q> and <q>darkness</q> constitute perceptually relevant
|
||||
dimensions for a high-level description of music. By decoding the
|
||||
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#references
|
||||
-#(style="width:44.5%;display:inline-block;float:right")
|
||||
%h1 References
|
||||
%ul.literatur
|
||||
%li
|
||||
%span.author Czedik-Eysenberg, I., Knauf, D., & Reuter, C.
|
||||
%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= link 'https://doi.org/10.18420/in2017_06'
|
||||
%li
|
||||
%span.author Grey, J.M.
|
||||
%span.year 1975
|
||||
%span.title An Exploration of Musical Timbre
|
||||
%span.herausgeber Stanford University, CCRMA Report No.STAN-M-2
|
||||
%li
|
||||
%span.author Li,T., Ogihara,M.
|
||||
%span.year 2003
|
||||
%span.title Detecting emotion in music
|
||||
%nobr
|
||||
%span.herausgeber 4th ISMIR Washington & Baltimore
|
||||
%span.pages 239-240
|
||||
%li
|
||||
%span.author Huron, D.
|
||||
%span.year 2008
|
||||
%span.title A comparison of average pitch height and interval size in major-and minor-key themes
|
||||
%nobr
|
||||
%span.herausgeber Empirical Musicology Review, 3
|
||||
%span.pages 59-63
|
||||
%li
|
||||
%span.author Siddiq,S. et al.
|
||||
%span.year 2014
|
||||
%span.title Kein Raum für Klangfarben - Timbre Spaces im Vergleich
|
||||
%nobr
|
||||
%span.herausgeber 40. DAGA
|
||||
%span.pages 56-57
|
||||
.clear
|
||||
|
|
|
|||
105
style.scss
105
style.scss
|
|
@ -63,7 +63,6 @@ header {
|
|||
}
|
||||
|
||||
h1 {
|
||||
//font-family: "Italianno";
|
||||
font-weight: normal;
|
||||
margin: 0 {
|
||||
//bottom: 0.5rem;
|
||||
|
|
@ -101,7 +100,7 @@ header {
|
|||
padding: 0 1rem 0 1rem;
|
||||
position: relative;
|
||||
|
||||
color: #bbb;
|
||||
color: #ddd;
|
||||
text-shadow: 0 0 5px black, 0 0 10px black, 0 0 15px black;
|
||||
//text-stroke: 1px black;
|
||||
//-webkit-text-stroke: 1px black;
|
||||
|
|
@ -132,11 +131,14 @@ header, main, footer {
|
|||
}
|
||||
|
||||
footer {
|
||||
padding-top: 0.5em;
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
padding: 0 0.45em 0 0.45em;
|
||||
//padding-top: 0.5em;
|
||||
section {
|
||||
padding: 2.25rem 0.5rem 0.25rem 0.5rem;
|
||||
//padding: 2.25rem 0.5rem 0.25rem 0.5rem;
|
||||
h1:first-child {
|
||||
margin: (-2.25rem) -0.5rem 0.25rem -0.5rem;
|
||||
//margin: (-2.25rem) -0.5rem 0.25rem -0.5rem;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -144,6 +146,7 @@ footer {
|
|||
body {
|
||||
margin: 0;
|
||||
background: url(brushed-metal.dark.svg), url(files/marble_black.png), #252220;
|
||||
//background: #252220;
|
||||
color: #565655;
|
||||
font-family: "Cardo";
|
||||
}
|
||||
|
|
@ -166,7 +169,7 @@ section {
|
|||
font-size: 0.95em;
|
||||
//text-align: justify;
|
||||
|
||||
&:first-child + * {
|
||||
& + * {
|
||||
margin-top: 1em;
|
||||
}
|
||||
|
||||
|
|
@ -187,7 +190,10 @@ section {
|
|||
&::before {
|
||||
z-index: -1;
|
||||
//background: linear-gradient( rgba(44, 58, 41, 0.8) 2.2rem, rgba(256, 256, 256, 0.8) 2.3rem );
|
||||
background: linear-gradient( rgba(49, 206, 15, 0.8) 2.2rem, rgba(256, 256, 256, 0.8) 2.3rem );
|
||||
//background: linear-gradient( rgba(101, 42, 7, 0.8) 2.2rem, rgba(256, 256, 256, 0.85) 2.3rem );
|
||||
//background: linear-gradient( rgba(0, 99, 166, 0.8) 2.2rem, rgba(256, 256, 256, 0.85) 2.3rem );
|
||||
//background: linear-gradient( rgba(187, 187, 187, 0.8) 2.2rem, rgba(256, 256, 256, 0.85) 2.3rem );
|
||||
background: linear-gradient( rgba(78, 83, 159, 0.8) 2.2rem, rgba(256, 256, 256, 0.85) 2.3rem );
|
||||
content: "";
|
||||
//border-radius: 2rem 2rem 0.5rem 0.5rem;
|
||||
position: absolute;
|
||||
|
|
@ -195,7 +201,7 @@ section {
|
|||
right: 0;
|
||||
bottom: 0;
|
||||
left: 0;
|
||||
box-shadow: 0 0 1rem #555;
|
||||
box-shadow: 0 0 1rem black;
|
||||
-webkit-print-color-adjust: exact;
|
||||
-webkit-filter: opacity(1);
|
||||
}
|
||||
|
|
@ -207,18 +213,31 @@ section {
|
|||
//border-bottom: 0.3rem solid black
|
||||
//border-radius: 0.18rem 1.68rem 0 0
|
||||
font-size: 1.8rem;
|
||||
color: orange;
|
||||
//color: #0063a6;
|
||||
color: #ddd;
|
||||
line-height: normal;
|
||||
text-align: center;
|
||||
font-family: "Italianno";
|
||||
font-weight: normal;
|
||||
|
||||
//border-radius: 0.5rem 2rem 0 0
|
||||
//padding: 0.1em 0.5rem;
|
||||
margin: (-2.5rem) -1rem 0.5rem -1rem;
|
||||
margin: (-2.25rem) -1rem 0.75rem -1rem;
|
||||
|
||||
//background-color: rgba(128,128,256,0.8)
|
||||
}
|
||||
h1, h2 {
|
||||
font-family: "PT Slab";
|
||||
font-weight: normal;
|
||||
margin: 0;
|
||||
}
|
||||
h2 {
|
||||
line-height: normal;
|
||||
}
|
||||
}
|
||||
|
||||
sup {
|
||||
font-size: 0.65em;
|
||||
vertical-align: top;
|
||||
line-height: 1em;
|
||||
}
|
||||
|
||||
quellen {
|
||||
|
|
@ -254,11 +273,11 @@ quellen {
|
|||
}
|
||||
|
||||
#column1_1, #column1_2, #column1_3,
|
||||
#column2_1, #column2_2 {
|
||||
#column2_1, #column2_2, #column2_3 {
|
||||
display: inline-block;
|
||||
box-sizing: border-box;
|
||||
margin: 0;
|
||||
padding: 0 1em 0.5em 1em;
|
||||
padding: 0 0.3em 0.5em 0.3em;
|
||||
vertical-align: top;
|
||||
position: relative;
|
||||
|
||||
|
|
@ -275,7 +294,7 @@ quellen {
|
|||
}
|
||||
|
||||
#column1_1 {
|
||||
width: 33%;
|
||||
width: 29%;
|
||||
//padding-right: 0.5em;
|
||||
}
|
||||
|
||||
|
|
@ -283,21 +302,24 @@ quellen {
|
|||
//float: right;
|
||||
//padding-left: 0.7em;
|
||||
//margin-left: -0.5em;
|
||||
width: 33%;
|
||||
width: 41%;
|
||||
}
|
||||
#column1_3 {
|
||||
//float: right;
|
||||
//padding-left: 0.7em;
|
||||
//margin-left: -0.5em;
|
||||
width: 33%;
|
||||
width: 29%;
|
||||
}
|
||||
|
||||
#column2_1 {
|
||||
width: 49%;
|
||||
width: 30%;
|
||||
}
|
||||
#column2_2 {
|
||||
width: 49%;
|
||||
}
|
||||
#column2_3 {
|
||||
width: 20%;
|
||||
}
|
||||
|
||||
.logos {
|
||||
width: 19rem;
|
||||
|
|
@ -350,6 +372,9 @@ h1 {
|
|||
font-family: "Cardo";
|
||||
//font-weight: normal;
|
||||
}
|
||||
h2 {
|
||||
font-family: "Cardo";
|
||||
}
|
||||
|
||||
em {
|
||||
color: #500;
|
||||
|
|
@ -375,15 +400,21 @@ feature {
|
|||
}
|
||||
|
||||
main {
|
||||
position: absolute;
|
||||
top: 10.5cm;
|
||||
right: 0;
|
||||
left: 0;
|
||||
text-align: center;
|
||||
&>*{
|
||||
text-align: initial;
|
||||
}
|
||||
position: relative;
|
||||
//top: 10.5cm;
|
||||
//right: 0;
|
||||
//left: 0;
|
||||
|
||||
/*img {
|
||||
margin: -0.5em;
|
||||
}*/
|
||||
}
|
||||
|
||||
main, footer {
|
||||
figure {
|
||||
margin: 0;
|
||||
&.left {
|
||||
|
|
@ -411,6 +442,12 @@ main {
|
|||
clear: left;
|
||||
}
|
||||
}
|
||||
&.pfifty {
|
||||
width: 47%;
|
||||
display: inline-block;
|
||||
vertical-align: bottom;
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
&.quarterly {
|
||||
float: right;
|
||||
|
|
@ -462,10 +499,11 @@ footer #literatur {
|
|||
table {
|
||||
border-collapse: collapse;
|
||||
border-spacing: 0;
|
||||
font-size: 0.8em;
|
||||
|
||||
th, td {
|
||||
border: 1px solid #aaa;
|
||||
padding: 0.1em;
|
||||
padding: 0.1em 0.5em;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -549,9 +587,10 @@ ul.literatur {
|
|||
}
|
||||
|
||||
figcaption {
|
||||
font-size: 0.8em;
|
||||
font-size: 0.45em;
|
||||
font-style: italic;
|
||||
margin-bottom: 1em;
|
||||
//margin-bottom: 1em;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
jbr {
|
||||
|
|
@ -559,3 +598,19 @@ jbr {
|
|||
width: 100%;
|
||||
height: 0;
|
||||
}
|
||||
|
||||
.blockarrow {
|
||||
line-height: 1em;
|
||||
position: absolute;
|
||||
text-align: center;
|
||||
font-size: 4.5rem;
|
||||
//color: #652a07;
|
||||
color: #bbb;
|
||||
text-shadow: 0 0 0.1em black, 0 0 0.1em black, 0 0 0.1em black;
|
||||
}
|
||||
|
||||
.col2center {
|
||||
td:first-child + td {
|
||||
text-align: center;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue