Global ETD Search

1	Melizmų sintezė dirbtinių neuronų tinklais / Melisma Synthesis Using Artificial Neural Networks Leonavičius, Romas 12 January 2007 (has links) Modern methods of speech synthesis are not suitable for restoration of song signals due to lack of vitality and intonation in the resulted sounds. The aim of presented work is to synthesize melismas met in Lithuanian folk songs, by applying Artificial Neural Networks. An analytical survey of rather a widespread literature is presented. First classification and comprehensive discussion of melismas are given. The theory of dynamic systems which will make the basis for studying melismas is presented and finally the relationship for modeling a melisma with nonlinear and dynamic systems is outlined. Investigation of the most widely used Linear Prediction Coding method and possibilities of its improvement. The modification of original Linear Prediction method based on dynamic LPC frame positioning is proposed. On its basis, the new melisma synthesis technique is presented. Developed flexible generalized melisma model, based on two Artificial Neural Networks – a Multilayer Perceptron and Adaline – as well as on two network training algorithms – Levenberg- Marquardt and the Least Squares error minimization – is presented. Moreover, original mathematical models of Fortis, Gruppett, Mordent and Trill are created, fit for synthesizing melismas, and their minimal sizes are proposed. The last chapter concerns experimental investigation, using over 500 melisma records, and corroborates application of the new mathematical models to melisma synthesis of one performer. Electronics and Electrical Engineering Mordentas Fortis Mordent Gruppett Dirbtinių neuronų tinklai Grupetas TPK Trelė Adaline Daina Song Sintezė Synthesis VNR Artificial neural network Melizma LPC Multilayer perceptron DNT Tiesinės prognozės koeficientai ANT Levenberg-Marquardt Mean opinion score Linear prediction coding Foršlagas Adalina Daugiasluoksnis perceptronas Melisma MOS Vidutinės nuomonės rezultatas Trill
2	Melizmų sintezė dirbtinių neuronų tinklais / Melisma Synthesis Using Artificial Neural Networks Leonavičius, Romas 12 January 2007 (has links) Modern methods of speech synthesis are not suitable for restoration of song signals due to lack of vitality and intonation in the resulted sounds. The aim of presented work is to synthesize melismas met in Lithuanian folk songs, by applying Artificial Neural Networks. An analytical survey of rather a widespread literature is presented. First classification and comprehensive discussion of melismas are given. The theory of dynamic systems which will make the basis for studying melismas is presented and finally the relationship for modeling a melisma with nonlinear and dynamic systems is outlined. Investigation of the most widely used Linear Prediction Coding method and possibilities of its improvement. The modification of original Linear Prediction method based on dynamic LPC frame positioning is proposed. On its basis, the new melisma synthesis technique is presented. Developed flexible generalized melisma model, based on two Artificial Neural Networks – a Multilayer Perceptron and Adaline – as well as on two network training algorithms – Levenberg- Marquardt and the Least Squares error minimization – is presented. Moreover, original mathematical models of Fortis, Gruppett, Mordent and Trill are created, fit for synthesizing melismas, and their minimal sizes are proposed. The last chapter concerns experimental investigation, using over 500 melisma records, and corroborates application of the new mathematical models to melisma synthesis of one performer. Electronics and Electrical Engineering Melisma Grupetas Mean opinion score Foršlagas Trill Mordentas Dirbtinių neuronų tinklai VNR TPK Song Synthesis Melizma Adalina Vidutinės nuomonės rezultatas Artificial neural network Gruppett Linear prediction coding LPC DNT Daugiasluoksnis perceptronas Daina ANT MOS Levenberg-Marquardt Multilayer perceptron Mordent Tiesinės prognozės koeficientai Fortis Adaline Sintezė Trelė
3	Sigrid Hjerténs och Isaac Grünewalds strandbilder år 1917-1918. : En bildsemiotisk analys ur ett kritiskt vithetsperspektiv. Kristensson, Maria January 2024 (has links) Syftet med uppsatsen är att utforska en ofta förbisedd genre hos två av de första svenska modernisterna Sigrid Hjertén och Isaac Grünewald, nämligen de strandbilder konstnärsparet skapade i samband med sina sommarsemestrar i Danmark åren 1917–1918. Hur skildrar konstnärerna sitt bad och strandliv och avviker dessa bilder från konstnärernas övriga produktion från samma tidpunkt? Uppsatsens metod utgår från C.S. Peirces semiotiska begrepp ikon, index och symbol. Ett annat syfte är att ur ett kritiskt vithetsperspektiv studera om de valda verken, Blixten och Den gröna badvagnen av Isaac Grünewald samt Badscen och Komposition av Sigrid Hjertén, upprättar eller reproducerar vithet som norm? Resultatet visar att så sker, både i verk, titlar och texter. Resultatet visar även att strandbilderna följer samma mönster som konstnärernas övriga produktion. I uppsatsen presenteras en ny tolkning av symbolerna i vissa av Isaac Grünewalds verk mellan åren 1914–1919, baserad på inflytande från baltiska folksånger (daina) och det politiska läget i ett sönderfallande Tsarryssland. Inflytandet från läraren Henri Matisse samt konststilen expressionismen syns tydligt hos båda konstnärerna. semiotic critical whiteness perspective Sigrid Hjertén Isaac Grünewald bildsemiotik kritiskt vithetsperspektiv Charles Sanders Peirce Görel Cavalli-Björkman Orvar Löfgren Per I Gedin Jeff Werner Richard Dyer vithetsstudier Ludwig Qvarnström Michel Eugéne Chevreul Henri Matisse Den gröna badvagnen Blixten friluftsideal rasbiologi parasoll expressionism kosmopolitism primitivism Fanö Gilleleje baltisk Det sjungande trädet daina Krisjanis Baron Michael Strmiska Den röd och vita hästen Kosacken gobeläng Annika Ekdahl Tobias Hübinette Irena Pundure Humanities and the Arts Humaniora och konst Arts Konst Art History Konstvetenskap

1

Page generated in 0.0397 seconds