Vizualizacija in razvoj analitičnega orodja s kompozicionalnim hierarhičnim modelom : diplomsko delo

Zakrajšek, Luka (author), Divjak, Saša (mentor), Marolt, Matija (comentor)

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.

• Language: Slovenian
• Keywords: kompozicionalni hierarhični model, nenegativna matrična faktorizacija, pridobivanje informacij iz glasbe, transkripcija
• Work type: Bachelor thesis/paper
• Typology: 2.11 - Undergraduate Thesis
• Organization: FRI - Faculty of Computer and Information Science
• Publisher: [L. Zakrajšek]
• Year: 2016
• Number of pages: 64 str.
• PID: 20.500.12556/RUL-80168
• COBISS.SI-ID: 1536771267
• Publication date in RUL: 01.02.2016

Licences

• License: CC BY-SA 2.5 SI, Creative Commons Attribution-ShareAlike 2.5 Slovenia
• Link: https://creativecommons.org/licenses/by-sa/2.5/si/deed.en
• Description: You are free to reproduce and redistribute the material in any medium or format. You are free to remix, transform, and build upon the material for any purpose, even commercially. You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original. You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

Secondary language

• Language: English
• Title: Visualization and analysis of musical recordings using compositional hierarchycal model

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.

• Keywords: compositional hierarchical model, non-negative matrix factorization, music information retrieval, transcription