Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Deep Layered Learning in MIR
KTH, School of Electrical Engineering and Computer Science (EECS), Speech, Music and Hearing, TMH.ORCID iD: 0000-0002-4957-2128
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Deep learning has boosted the performance of many music information retrieval (MIR) systems in recent years. Yet, the complex hierarchical arrangement of music makes end-to-end learning hard for some MIR tasks – a very deep and structurally flexible processing chain is necessary to extract high-level features from a spectrogram representation. Mid-level representations such as tones, pitched onsets, chords, and beats are fundamental building blocks of music. This paper discusses how these can be used as intermediate representations in MIR to facilitate deep processing that generalizes well: each music concept is predicted individually in learning modules that are connected through latent representations in a directed acyclic graph. It is suggested that this strategy for inference, defined as deep layered learning (DLL), can help generalization by (1) – enforcing the validity of intermediate representations during processing, and by (2) – letting the inferred representations establish disentangled structures that support high-level invariant processing. A background to DLL and modular music processing is provided, and relevant concepts such as pruning, skip connections, and layered performance supervision are reviewed.

National Category
Other Computer and Information Science Computer Engineering Computer Sciences
Research subject
Computer Science; Information and Communication Technology
Identifiers
URN: urn:nbn:se:kth:diva-226893OAI: oai:DiVA.org:kth-226893DiVA, id: diva2:1201890
Note

QC 20180427

arXiv preprint arXiv:1804.07297

Available from: 2018-04-26 Created: 2018-04-26 Last updated: 2018-04-27Bibliographically approved
In thesis
1. Modeling Music: Studies of Music Transcription, Music Perception and Music Production
Open this publication in new window or tab >>Modeling Music: Studies of Music Transcription, Music Perception and Music Production
2018 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This dissertation presents ten studies focusing on three important subfields of music information retrieval (MIR): music transcription (Part A), music perception (Part B), and music production (Part C).

In Part A, systems capable of transcribing rhythm and polyphonic pitch are described. The first two publications present methods for tempo estimation and beat tracking. A method is developed for computing the most salient periodicity (the “cepstroid”), and the computed cepstroid is used to guide the machine learning processing. The polyphonic pitch tracking system uses novel pitch-invariant and tone-shift-invariant processing techniques. Furthermore, the neural flux is introduced – a latent feature for onset and offset detection. The transcription systems use a layered learning technique with separate intermediate networks of varying depth.  Important music concepts are used as intermediate targets to create a processing chain with high generalization. State-of-the-art performance is reported for all tasks.

Part B is devoted to perceptual features of music, which can be used as intermediate targets or as parameters for exploring fundamental music perception mechanisms. Systems are proposed that can predict the perceived speed and performed dynamics of an audio file with high accuracy, using the average ratings from around 20 listeners as ground truths. In Part C, aspects related to music production are explored. The first paper analyzes long-term average spectrum (LTAS) in popular music. A compact equation is derived to describe the mean LTAS of a large dataset, and the variation is visualized. Further analysis shows that the level of the percussion is an important factor for LTAS. The second paper examines songwriting and composition through the development of an algorithmic composer of popular music. Various factors relevant for writing good compositions are encoded, and a listening test employed that shows the validity of the proposed methods.

The dissertation is concluded by Part D - Looking Back and Ahead, which acts as a discussion and provides a road-map for future work. The first paper discusses the deep layered learning (DLL) technique, outlining concepts and pointing out a direction for future MIR implementations. It is suggested that DLL can help generalization by enforcing the validity of intermediate representations, and by letting the inferred representations establish disentangled structures supporting high-level invariant processing. The second paper proposes an architecture for tempo-invariant processing of rhythm with convolutional neural networks. Log-frequency representations of rhythm-related activations are suggested at the main stage of processing. Methods relying on magnitude, relative phase, and raw phase information are described for a wide variety of rhythm processing tasks.

Abstract [sv]

Denna avhandling presenterar tio studier inom tre viktiga delområden av forskningsområdet ”Music Information Retrieval” (MIR) – ett forskningsområde fokuserat på att extrahera information från musik. Del A riktar in sig på musiktranskription, del B på musikperception och del C på musikproduktion. En avslutande del diskuterar maskininlärningsmetodiken och spanar framåt (del D).

I del A presenteras system som kan transkribera musik med hänsyn till rytm och polyfon tonhöjd. De två första publikationerna beskriver metoder för att estimera tempo och positionen av taktslag i ljudande musik. En metod för att beräkna den mest framstående periodiciteten (”cepstroiden”) beskrivs, samt hur denna kan användas för att guida de applicerade maskininlärningssystemen.  Systemet för polyfon tonhöjdsestimering kan både identifiera ljudande toner samt notstarter- och slut. Detta system är både tonhöjdsinvariant samt invariant med hänseende till variationer över tid inom ljudande toner. Transkriptionssystemen tränas till att predicera flera musikaspekter i en hierarkisk struktur. Transkriptionsresultaten är de bästa som rapporterats i tester på flera olika dataset.

Del B fokuserar på perceptuella särdrag i musik. Dessa kan prediceras för att modellera fundamentala perceptionsaspekter, men de kan också användas som representationer i modeller som försöker klassificera övergripande musikparametrar. Modeller presenteras som kan predicera den upplevda hastigheten samt den upplevda dynamiken i utförandet med hög precision. Medelvärdesbildade skattningar från omkring 20 lyssnare utgör målvärden under träning och evaluering.

I del C utforskas aspekter relaterade till musikproduktion. Den första studien analyserar variationer i medelvärdesspektrum mellan populärmusikaliska musikstycken. Analysen visar att nivån på perkussiva instrument är en viktig faktor för spektrumdistributionen – data antyder att denna nivå är bättre att använda än genreklassificeringar för att förutsäga spektrum. Den andra studien i del C behandlar musikkomposition. Ett algoritmiskt kompositionsprogram presenteras, där relevanta musikparametrar fogas samman en hierarkisk struktur. Ett lyssnartest genomförs för att påvisa validiteten i programmet och undersöka effekten av vissa parametrar.

Avhandlingen avslutas med del D, vilken placerar den utvecklade maskininlärningstekniken i ett vidare sammanhang och föreslår nya metoder för att generalisera rytmprediktion. Den första studien diskuterar djupinlärningssystem som predicerar olika musikaspekter i en hierarkisk struktur. Relevanta koncept presenteras tillsammans med förslag för framtida implementationer. Den andra studien föreslår en tempoinvariant metod för att processa log-frekvensdomänen av rytmsignaler med så kallade convolutional neural networks. Den föreslagna arkitekturen kan använda sig av magnitud, relative fas mellan rytmkanaler, samt ursprunglig fas från frekvenstransformen för att ta sig an flera viktiga problem relaterade till rytm.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2018. p. 49
Series
TRITA-EECS-AVL ; 2018-35
Keywords
Music Information Retrieval, MIR, Music, Music Transcription, Music Perception, Music Production, Tempo Estimation, Beat Tracking, Polyphonic Pitch Tracking, Polyphonic Transcription, Music Speed, Music Dynamics, Long-time average spectrum, LTAS, Algorithmic Composition, Deep Layered Learning, Convolutional Neural Networks, Rhythm Tracking, Ensemble Learning, Perceptual Features, Representation Learning
National Category
Other Computer and Information Science Computer Engineering Media and Communication Technology
Identifiers
urn:nbn:se:kth:diva-226894 (URN)978-91-7729-768-0 (ISBN)
Public defence
2018-05-18, D3, Kungliga Tekniska Högskolan, Lindstedtsvägen 5, Stockholm, 13:00 (English)
Opponent
Supervisors
Note

QC 20180427

Available from: 2018-04-27 Created: 2018-04-26 Last updated: 2018-05-03Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

ResearchGate PDF; also avilable at arXiv

Search in DiVA

By author/editor
Elowsson, Anders
By organisation
Speech, Music and Hearing, TMH
Other Computer and Information ScienceComputer EngineeringComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 22 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf