diplomsko delo
Luka Zakrajšek (Author), Saša Divjak (Mentor), Matija Marolt (Co-mentor)

Abstract

V diplomski nalogi razvijemo orodje za vizualizacijo in analizo glasbenih posnetkov z uporabo kompozicionalnega hierarhičnega modela. Model omogoča učenje konceptov tonov iz monofoničnih posnetkov, transparenten vpogled v naučene strukture ter robustno in hitro obdelavo zvočnih posnetkov. Nadgradimo ga z metodo diskriminativne nenegativne matrične faktorizacije. S to metodo se lahko zelo dobro prilagodimo polifoničnim posnetkom. Uvedli smo tudi različne tehnike čiščenja hipotez o prisotnosti tonskih višin, s katerimi izboljšamo končne rezultate. Model preizkusimo na zbirki polifoničnih klavirskih posnetkov, vokalni zbirki ljudskih pesmi ter na sintetizirani zbirki različnih inštrumentov. Z modelom CHM in nadgradnjo DNMF dobimo zelo dobre rezultate, zato model uporabimo kot osnovo za spletno aplikacijo. Aplikacija omogoča nalaganje novih zvočnih posnetkov, učenje in testiranje novih modelov, grafično predstavitev naučenih struktur ter pogled klavirske tabulature. Slednji omogoča analizo pridobljenih transkripcij, interaktivno urejanje in dodajanje ritmičnih anotacij ter izvoz v druga orodja.

Keywords

kompozicionalni hierarhični model;nenegativna matrična faktorizacija;pridobivanje informacij iz glasbe;transkripcija;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [L. Zakrajšek]
UDC: 004.774:78(043.2)
COBISS: 1536771267 Link will open in a new window
Views: 1679
Downloads: 535
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Visualization and analysis of musical recordings using compositional hierarchical model
Secondary abstract: This thesis provides a tool for visualization and analysis of music recordings using compositional hierarchical model. Model learns the concept of music tones from monophonic recordings, transparent insight into learned structures and also robust and fast processing of sound recordings. Model is extended with discriminative non-negative matrix factorization method. With this method we can get a really good fit for polyphonic recordings. We introduced various techniques for pitch hipothesis cleaning that improve final results. Model is evaluated on polyphonic piano recording database, vocal collection of folk music and synthesized collection of various instruments. We achieve very significant results using CHM and DNMF and use CHM as a basis for the web application. Application can be used to upload new sound recordings, learn and test new models, observe graphical representation of learned structures and piano roll view. Piano roll helps us analyze generated transcriptions, interactive editing, adding rhythmic annotations and export data for further manipulation using other software products.
Secondary keywords: compositional hierarchical model;non-negative matrix factorization;music information retrieval;transcription;computer and information science;diploma;
File type: application/pdf
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 64 str.
ID: 9122962