Original title: Identifikace cover verzí skladeb pomocí harmonických příznaků, modelu harmonie a harmonické složitosti
Translated title: Cover Song Identification using Music Harmony Features, Model and Complexity Analysis
Authors: Maršík, Ladislav ; Pokorný, Jaroslav (advisor) ; Ge, Mouzhi (referee) ; Łukasik, Ewa (referee)
Document type: Doctoral theses
Year: 2019
Language: eng
Abstract: [eng] [cze]
Title: Cover Song Identification using Music Harmony Features, Model and Complexity Analysis Author: Ladislav Maršík Department: Department of Software Engineering Supervisor: Prof. RNDr. Jaroslav Pokorný, CSc., Department of Software Engineering Abstract: Analysis of digital music and its retrieval based on the audio fe- atures is one of the popular topics within the music information retrieval (MIR) field. Every musical piece has its characteristic harmony structure, but harmony analysis is seldom used for retrieval. Retrieval systems that do not focus on similarities in harmony progressions may consider two versions of the same song different, even though they differ only in instrumentation or a singing voice. This thesis takes various paths in exploring, how music harmony can be used in MIR, and in particular, the cover song identification (CSI) task. We first create a music harmony model based on the knowledge of music theory. We define novel concepts: a harmonic complexity of a mu- sical piece, as well as the chord and chroma distance features. We show how these concepts can be used for retrieval, complexity analysis, and how they compare with the state-of-the-art of music harmony modeling. An extensive comparison of harmony features is then performed, using both the novel fe- atures and the... Title: Identifikace cover verzí skladeb pomocí harmonických příznaků, mo- delu harmonie a harmonické složitosti Author: Ladislav Maršík Department: Department of Software Engineering Supervisor: Prof. RNDr. Jaroslav Pokorný, CSc., Department of Software Engineering Abstract: Analýza digitálnej hudby a jej efektívne vyhl'adávanie založené na príznakoch je populárnou témou v rámci odvetvia music information re- trieval (MIR). Každé hudobné dielo má svoju charakteristickú harmonickú štruktúru, ale jej analýza sa používa na vyhl'adávanie len zriedka. Pokial' aplikácia neporovnáva akordický priebeh skladby, môže sa stat' že nesprávne vyhlási dve skladby za rôzne, aj ked' sa v skutočnosti odlišujú len zmenou nástrojov alebo speváka. V tejto práci ukážeme viaceré možnosti ako využit' hudobnú harmóniu pre MIR, a to hlavne pre detekciu cover verzií skladieb. Najprv sa venujeme vytvoreniu modelu hudobnej harmónie na základe hu- dobnej teórie. Definujeme nové koncepty: harmonickú zložitost', akordické vzdialenosti a vzdialenosti medzi chroma vektormi. Ukážeme ako tieto kon- cepty využit' pre vyhl'adávanie, analýzu a porovnáme náš model s modernými modelmi hudobnej kognície. V d'alšej časti sa venujeme dôkladnému porov- naniu harmonických...
Keywords: chord distance; chroma vector distance; cover song identification; dynamic time warping; feature extraction; karaoke dataset; music harmony analysis; music information retrieval; neural networks; akordická vzdálenost; analýza hudební harmonie; dynamic time warping; extrakce příznaků; identifikace cover verzí; karaoke dataset; music information retrieval; neurónové sítě; vzdálenost chroma vektorů

Institution: Charles University Faculties (theses) (web)
Document availability information: Available in the Charles University Digital Repository.
Original record: http://hdl.handle.net/20.500.11956/111319

Permalink: http://www.nusl.cz/ntk/nusl-408150


The record appears in these collections:
Universities and colleges > Public universities > Charles University > Charles University Faculties (theses)
Academic theses (ETDs) > Doctoral theses