deac/poster
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

pink edition.

Browse source
This commit is contained in:
Denis Knauf 2018-07-15 12:13:49 +02:00
parent 947a22c2ff
commit 12c985471a
3 changed files with 301 additions and 155 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

52
brushed-metal.pink.svg Normal file
View file

@ -0,0 +1,52 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<svg
xmlns:svg="http://www.w3.org/2000/svg"
xmlns="http://www.w3.org/2000/svg"
width="841mm"
height="1189mm"
viewBox="0 0 2979.9213 4212.9921"
version="1.1">
<defs>
<filter
style="color-interpolation-filters:sRGB;"
id="filter4686">
<feTurbulence
type="fractalNoise"
numOctaves="3"
baseFrequency="0.002 1"
seed="0"
result="result0" />
<feColorMatrix
result="result4"
values="0"
type="saturate" />
<feComposite
in="SourceGraphic"
in2="result4"
operator="arithmetic"
k1="0.40000000000000002"
k2="0.69999999999999996"
k3="0.14999999999999999"
result="result2"
k4="0.050000000000000003" />
<feBlend
result="result5"
mode="normal"
in="result2"
in2="SourceGraphic" />
<feComposite
in="result5"
in2="SourceGraphic"
operator="in"
result="result3" />
</filter>
</defs>
<g transform="translate(0,3160.6299)">
<rect
style="fill:#ff07ef;filter:url(#filter4686)"
width="3054.7012"
height="4283.0469"
x="-16.162441"
y="-3182.1973" />
</g>
</svg>
Side by side

After

Width:  |  Height:  |  Size: 1.3 KiB

363
index.html.haml
View file

@ -15,10 +15,10 @@
- content = Base64.urlsafe_encode64 File.read( file)
- "data:#{mime_type};base64,#{content}"
!!! 5
%html(lang='de')
%html(lang='en')
%head
-#%meta(charset="utf-8")
%title “Düsterkeit” in der Musik: Physikalische Entsprechungen und Vorhersagemodelle
%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/PT_Mono.css")
@ -39,9 +39,9 @@
%body
%header(style="")
%figure.logos(style="margin-top:0.3cm")<>
%img#uni-logo(src="files/Uni_Logo_2016_ausschnitt.gif")
%img#tagungs-logo(style="float:right" src="files/daga-2018-logo.png")
%div(style="font-size:0.8em;margin-top:1.31cm")
%img#tagungs-logo(style="float:right" src="files/icmpc15_logo.jpg")
%img#uni-logo(src="files/univie_logo.png")
-#%div(style="font-size:0.8em;margin-top:1.31cm")
44. Jahrestagung für Akustik
%br<>
Technische Universität München
@ -52,103 +52,230 @@
.grabstein-wo Technische Universität München
.grabstein-von &#10022; 19. März 2018
.grabstein-bis &#10013; 22. März 2018
%img(style="height:7cm;top:3cm;right:24cm;position:absolute" alt="Dunkle Nacht" src="files/Candle.png")
-#%img(style="height:7cm;top:3cm;right:24cm;position:absolute" alt="Dunkle Nacht" src="files/Candle.png")
%h1
<q>Düsterkeit</q> in der Musik:
-#%br<>
Physikalische Entsprechungen und Vorhersagemodelle
Decoding the sound of <q>hardness</q> and <q>darkness</q> as perceptual dimensions of music
%p#authors<>
%span.author(data-mark="1,2")<> Isabella Czedik-Eysenberg
%span.author(data-mark="1")<> Christoph Reuter
%span.author(data-mark="2")<> Denis Knauf
%p#institutions<>
%span.institution(data-mark="1")<> Institut für Musikwissenschaft, Universität Wien
%span.institution(data-mark="2")<> Informatik, Technische Universität Wien
%span.institution(data-mark="1")<> University of Vienna, Austria
%span.institution(data-mark="2")<> Student at Technical University of Vienna, Austria
%main
#column1
%section#hintergrund
%h1 1. Hintergrund
%p
Von Dowlands <q>Songs of Darkness</q> bis hin zu Genres wie Gothic oder
Doom Metal ist <q>Düsterkeit</q> eine Dimension von Musik, die sich auch
abseits melan-<jbr/>cholischer Texte im Klangbild niederschlagen kann.
%p
In musikalischen Adjektiv-Klassifikationen bildete der Begriff
<q>düster</q> (<q>dark</q>) einen gemeinsamen Cluster mit Trauer-bezogenen
Adjektiven (etwa <q>gloomy</q>, <q>sad</q>, <q>depressing</q>)
#{quellen Hevner: 1936}.
Jene Verknüpfung wurde auch in späteren Arbeiten zur automatisierten
musikalischen Affektdetektion aufgegriffen #{quellen 'Li & Ogihara'=>2003}.
Dies würde die Relevanz von Klangattributen,
welche mit dem Ausdruck von Trauer assoziiert sind – etwa
Moll-Tonarten oder auch tiefere Grundtonhöhen,
geringe Melodiebewegungen und ein <q>düsteres</q> Timbre
#{quellen Huron: 2008} – nahelegen.
%p
Von der Klangfarbenforschung ausgehend wird <q>Helligkeit</q> (messbar
an der spektralen Verteilung eines Klanges) häufig als eine zentrale
perzeptuelle Klangfarbendimension angesehen
#{quellen 'Wedin & Goude'=>1972, Bismarck: 1974, Grey: 1975, 'Siddiq et al.'=>2014}.
Dies wirft u.a. die Frage auf, ob es hierbei einen (umgekehrt
proportionalen) Zusammenhang gibt, bzw. welche anderen
zusätzlichen Faktoren zu einer klanglichen Düsterkeitsbewertung
beitragen.
#column1_1
%section#heavy_features
:markdown
Sound Features
==============
%section#fragestellung
%h1 2. Fragestellungen und Ziele
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
components.
%ol
%li
%p
Wie lässt sich das Wahrnehmungskonzept klanglicher <q>Düsterkeit</q>
anhand von Audiomerkmalen charakterisieren?
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")
%li
%p
Korreliert die empfundene klangliche <q>Düsterkeit</q> umgekehrt
proportional mit klangfarblicher <q>Helligkeit</q>?
dynamic distribution
%figure
%img(style="width:50%" src="files/blunt_envelope.png")
%img(style="width:50%" src="files/decap_envelope.png")
%figure
%img(style="width:50%" src="files/blunt_dyndist.png")
%img(style="width:50%" src="files/decap_dyndist.png")
%li
%p
Ziel ist die Erstellung eines Modells zur automatischen Vorhersage
der wahrgenommenen <q>Düsterkeit</q> von Musikstücken.
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
:markdown
Sequential feature selection
%section#methoden
%h1 3. Methoden
%p
150 Musikbeispiele aus 10 unterschiedlichen Subgenres der Bereiche
Metal, Techno, Gothic und Pop wurden anhand von Hörerstatistiken
der Internetplattform LastFM selektiert. Die Refrains dieser
Stücke wurden 40 Versuchspersonen zur Bewertung dargeboten, um
eine Ground Truth für die Wahrnehmung der <q>Düsterkeit</q> von
Musikbeispielen zu erheben. Unter Einsatz von Essentia
#{quellen 'Bogdanov et al.'=> 2013}, MIRtoolbox
#{quellen 'Lartillot & Toiviainen'=> 2007},
Loudness Toolbox #{quellen Genesis: 2009} und TSM Toolbox
#{quellen 'Driedger & Müller'=>2014} wurden 230
Signaleigenschaften über die spektrale Verteilung, zeitliche und
dynamische Klangfaktoren gewonnen. Diese wurden mittels Machine
Learning-Verfahren unter Kreuzvalidierung ausgewertet und kombiniert,
um auf Basis der Hörversuchsdaten Vorhersagemodelle zu erstellen.
* set of 5 features
* predictive linear regression model
%section#schlussfolgerungen
-#(style="width:44.5%;display:inline-block;float:left")
%h1 5. Diskussion/Schlussfolgerungen
%p
Es konnte anhand von Audiomerkmalen ein Modell zur Vorhersage
einer Bewertung musikalischer Düsterkeit aufgestellt werden
<nobr>(Korrelation r = 0,80, p &lt; 0,01)</nobr>.
%p
Eine Antiproportionalität mit klangfarblicher Helligkeit ließ sich
mit gängigen Maßen hierfür nicht nachweisen.
%p
Eine Gleichsetzung mit <q>traurig</q> scheint nicht 1:1 möglich zu sein,
sehr wohl finden sich aber starke Zusammenhänge (etwa Moll-Harmonik).
%p
Das Konzept soll in folgenden Untersuchungen genauer in Hinblick
auf das Interrater-Agreement und den Zusammenhang zu anderen
Wahrnehmungskonzepten betrachtet werden.
RMSE | 0.64
R-Squared | 0.80
MSE | 0.40
MAE | 0.49
r | 0.900
%figure
%img(src="scatter_hardness_model5.png")
%section#heavy_rater_agreement
:markdown
Rater Agreement
===============
#column2
%section#ergebnisse1(style="height:96.35cm")
Intraclass Correlation Coefficient (Two-Way Model, Consistency): <b>0.653</b>
#column1_2
-#%section#aims
%h1 Aims
%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
explored if there are interactions between the two factors and to
which extent it is possible to classify musical genres based on
these dimensions.
%section#method
%h1 Method
%figure.right(style="width:50%")
%img(src="files/LastFM.png")
:markdown
Based on last.fm listener statistics, 150 pieces of music were selected
from 10 different subgenres of metal, techno, gothic and pop music.
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:
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%")
%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
%section#further_resultes_conclusion
:markdown
Further Results &amp; Conclusions
=================================
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 &lt; 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%.
%img(src="files/predictionTree_genreAgg2.png")
%img(src="files/confusionMatrix_simpleTree_genreAgg2.png")
%section#conclusion
: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#ergebnisse1(style="height:96.35cm")
%h1 4. Ergebnisse
%figure.right(style="width:70%")
%img(alt='Verwelkter Mohn' src='files/violin_genre_darkMean.svg')
@ -253,65 +380,22 @@
%div(style="clear:left")
.clear
%footer
%section#literatur
%section#references
-#(style="width:44.5%;display:inline-block;float:right")
%h1 6. Literatur
%h1 References
%ul.literatur
%li
%span.author Bismarck, G. v.
%span.year 1974
%span.title Sharpness as an attribute of the timbre of steady sounds
%nobr
%span.book Acta Acustica united with Acustica 30.3
%span.pages 159–172
%li
%span.author Bogdanov, D., Wack N., Gómez E., Gulati S., Herrera P., Mayor O., et al.
%span.year 2013
%span.title ESSENTIA: an Audio Analysis Library for Music Information Retrieval
%nobr
%span.herausgeber International Society for Music Information Retrieval Conference (ISMIR'13)
%span.pages 493-498
%li
%span.author Driedger, J. &amp; Müller, M.
%span.year 2014
%span.title TSM Toolbox: MATLAB Implementations of Time-Scale Modification Algorithms
%span.herausgeber Proc. of the International Conference on Digital Audio Effects
%li
%span.author Genesis
%span.year 2009
%span.title Loudness toolbox
%span.author Czedik-Eysenberg, I., Knauf, D., &amp; 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
%a(href="http://www.genesis-acoustics.com/en/index.php?page=32")
http://www.genesis-acoustics.com/en/index.php?page=32
%a(href="https://doi.org/10.18420/in2017_06") 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 Hevner, K.
%span.year 1936
%span.title Experimental studies of the elements of expression in music
%nobr
%span.herausgeber The American Journal of Psychology, 48(2)
%span.pages 246-268
%li
%span.author Lartillot, O., &amp; Toiviainen, P.
%span.year 2007
%span.title A Matlab toolbox for musical feature extraction from audio
%nobr
%span.herausgeber International Conference on Digital Audio Effects, Bordeaux
%span.pages 237-244
%li
%span.author Laurier, C., Meyers, O., Serrà, J., Blech, M., Herrera, P., &amp; Serra, X.
%span.year 2010
%span.title Indexing music by mood: Design and integration of an automatic content-based annotator
%nobr
%span.herausgeber Multimedia Tools and Applications, 48(1)
%span.pages 161-184
%span.link
%a(href="http://dx.doi.org/10.1007/s11042-009-0360-2") http://dx.doi.org/10.1007/s11042-009-0360-2
%li
%span.author Li,T., Ogihara,M.
%span.year 2003
@ -333,11 +417,4 @@
%nobr
%span.herausgeber 40. DAGA
%span.pages 56-57
%li
%span.author Wedin, L. &amp; Goude, G.
%span.year 1972
%span.title Dimension analysis of the perception of instrumental timbre
%nobr
%span.herausgeber Scandinavian Journal of Psychology 13.1
%span.pages 228–240
.clear

41
style.scss
View file

@ -144,6 +144,7 @@ footer {
body {
margin: 0;
background: url(files/marble_black.png); //url(brushed-metal.new.svg);
background: url(brushed-metal.pink.svg);
color: #565655;
font-family: "Cardo";
}
@ -182,7 +183,8 @@ 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(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 );
content: "";
//border-radius: 2rem 2rem 0.5rem 0.5rem;
position: absolute;
@ -199,7 +201,7 @@ section {
//border-bottom: 0.3rem solid black
//border-radius: 0.18rem 1.68rem 0 0
font-size: 1.8rem;
color: white;
color: orange;
line-height: normal;
text-align: center;
font-family: "Italianno";
@ -245,7 +247,8 @@ quellen {
}
}
#column1, #column2 {
#column1_1, #column1_2, #column1_3,
#column2_1, #column2_2 {
display: inline-block;
box-sizing: border-box;
margin: 0;
@ -265,16 +268,29 @@ quellen {
}
}
#column1 {
width: 32%;
padding-right: 0.5em;
#column1_1 {
width: 33%;
//padding-right: 0.5em;
}
#column2 {
float: right;
padding-left: 0.7em;
margin-left: -0.5em;
width: 68%;
#column1_2 {
//float: right;
//padding-left: 0.7em;
//margin-left: -0.5em;
width: 33%;
}
#column1_3 {
//float: right;
//padding-left: 0.7em;
//margin-left: -0.5em;
width: 33%;
}
#column2_1 {
width: 49%;
}
#column2_2 {
width: 49%;
}
.logos {
@ -320,7 +336,8 @@ quellen {
}
q {
quotes: "„" "“";
//quotes: "„" "“";
quotes: "‘" "’";
}
h1 {