poster/index.html.haml
2018-07-17 22:42:44 +02:00

317 lines
13 KiB
Plaintext

- require "base64"
- def quellen opts
- etc = opts.key? :etc
- if etc
- opts.delete :etc
- etc = "\n<etc/>"
- else
- etc = ''
- "<quellen>#{opts.map {|k, v| "<quelle jahr=#{v}>#{k}</quelle>" }.join "\n"}#{etc}</quellen>"
- def link link
- "<a href=\"#{link}\">#{link}</a>"
- def import_data file
- 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
-#%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/PT_Mono.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")
-#%link(rel="stylesheet" href="fonts/BlackDahlia.css")
-#%link(rel="stylesheet" href="fonts/ThroughStruggleDEMO.css")
-#%link(rel="stylesheet" href="fonts/TheDefiler.css")
%link(rel="stylesheet" href="fonts/Cardo.css")
%link(rel="stylesheet" href="fonts/Italianno.css")
-#%link(rel="stylesheet" href="fonts/CinzelDecorative.css")
%link(rel="stylesheet" href="style.css")
%meta(name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no")
%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")
-#%div(style="font-size:0.8em;margin-top:1.31cm")
44. Jahrestagung für Akustik
%br<>
Technische Universität München
%br<>
19. März 2018 .. 22. März 2018
-#.grabstein
.grabstein-was DAGA
.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")
%h1
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")<> University of Vienna, Austria
%span.institution(data-mark="2")<> Student at Technical University of Vienna, Austria
%main
#column1_1
%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>.
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")
%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")
%li
melodic content / harmonic entropy
%figure
%img.fifty(src="files/blunt_chromagram.png")
%img.fifty(src="files/decap_chromagram.png")
:markdown
Model
-----
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")
:markdown
Rater Agreement
---------------
Intraclass Correlation Coefficient (Two-Way Model, Consistency): <b>0.653</b>
.clear
#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")
%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.
.clear
%h2 Data
%figure
%img(src="files/scatter_hard_dark_dashedline_2017-09-05.png")
.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
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%.
.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
==========
<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., &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= 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 &amp; 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