poster/index.html.haml

- 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#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<>
          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
              %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
              %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
              %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

          -#%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<>
            &darr;
            %br<>
            set of 5 features
            %br<>
            &darr;
            %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 <nobr>(Two-Way Model, Consistency): <b>0.653</b></nobr>
          .clear

      #column1_2
        %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
            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: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
            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

        -#.blockarrow(style="display:block;width:100%;font-size:6em;margin:0") &#129075;
        %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") &#129095;
          .blockarrow(style="bottom:9rem;left:-3rem") &#129092;
          .blockarrow(style="bottom:9rem;right:-3rem") &#129094;
          .clear
        %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") &#129095;
          %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
          %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>** 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.left
            %img(src="files/scatter_spectral_centroid_essentia_darkness.png")
          %div(style="height:1em")
          %p No evidence for negative correlations between darkness rating and measures for brightness:

          %div(style="text-align:center")
            %div(style="display:inline-block")
              :markdown
                Feature                | r     | p
                -----------------------|-------|----------
                <nobr>Spectral centroid</nobr>      | 0.334 | &lt;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 &lt; 0.01</nobr>
            according to t-test)
          %h2 Model
          %figure.fifty.right(style="width:67%;text-align:center;margin-bottom:3px")
            %img(src="files/scatter_darkness_model8.png")
            %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<>
            &darr;
            %br<>
            set of 8 features
            %br<>
            &darr;
            %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 <nobr>(Two-Way Model, Consistency):
            <b>0.498</b></nobr>
          .clear

    %footer(style="padding-top:0.2em")
      %section#further_resultes_conclusion(style="padding-bottom:0.20em")
        %h1 Further Results &amp; Conclusions
        %div
          #column2_1
            :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

          #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 &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.
            %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&nbsp;%.

          #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., &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