SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model
This paper presents a compositional hierarchical model for pattern discovery in symbolic music. The model can be regarded as a deep architecture with a transparent structure. It can learn a set of repeated patterns within individual works or larger corpora in an unsupervised manner, relying on stati...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/7/11/1135 |
| _version_ | 1819030119070564352 |
|---|---|
| author | Matevž Pesek Aleš Leonardis Matija Marolt |
| author_facet | Matevž Pesek Aleš Leonardis Matija Marolt |
| author_sort | Matevž Pesek |
| collection | DOAJ |
| description | This paper presents a compositional hierarchical model for pattern discovery in symbolic music. The model can be regarded as a deep architecture with a transparent structure. It can learn a set of repeated patterns within individual works or larger corpora in an unsupervised manner, relying on statistics of pattern occurrences, and robustly infer the learned patterns in new, unknown works. A learned model contains representations of patterns on different layers, from the simple short structures on lower layers to the longer and more complex music structures on higher layers. A pattern selection procedure can be used to extract the most frequent patterns from the model. We evaluate the model on the publicly available JKU Patterns Datasetsand compare the results to other approaches. |
| first_indexed | 2024-12-21T06:25:05Z |
| format | Article |
| id | doaj.art-fac6d84575ef464793af51649cef6dca |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T06:25:05Z |
| publishDate | 2017-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fac6d84575ef464793af51649cef6dca2022-12-21T19:13:09ZengMDPI AGApplied Sciences2076-34172017-11-01711113510.3390/app7111135app7111135SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical ModelMatevž Pesek0Aleš Leonardis1Matija Marolt2Faculty of Computer and Information Science, University of Ljubljana, Ljubljana 1000, SloveniaSchool of Computer Science, University of Birmingham, Edgbaston, Birmingham B15 2TT, U.KFaculty of Computer and Information Science, University of Ljubljana, Ljubljana 1000, SloveniaThis paper presents a compositional hierarchical model for pattern discovery in symbolic music. The model can be regarded as a deep architecture with a transparent structure. It can learn a set of repeated patterns within individual works or larger corpora in an unsupervised manner, relying on statistics of pattern occurrences, and robustly infer the learned patterns in new, unknown works. A learned model contains representations of patterns on different layers, from the simple short structures on lower layers to the longer and more complex music structures on higher layers. A pattern selection procedure can be used to extract the most frequent patterns from the model. We evaluate the model on the publicly available JKU Patterns Datasetsand compare the results to other approaches.https://www.mdpi.com/2076-3417/7/11/1135music information retrievalcompositional modellingpattern discoverysymbolic music representations |
| spellingShingle | Matevž Pesek Aleš Leonardis Matija Marolt SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model Applied Sciences music information retrieval compositional modelling pattern discovery symbolic music representations |
| title | SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model |
| title_full | SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model |
| title_fullStr | SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model |
| title_full_unstemmed | SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model |
| title_short | SymCHM—An Unsupervised Approach for Pattern Discovery in Symbolic Music with a Compositional Hierarchical Model |
| title_sort | symchm an unsupervised approach for pattern discovery in symbolic music with a compositional hierarchical model |
| topic | music information retrieval compositional modelling pattern discovery symbolic music representations |
| url | https://www.mdpi.com/2076-3417/7/11/1135 |
| work_keys_str_mv | AT matevzpesek symchmanunsupervisedapproachforpatterndiscoveryinsymbolicmusicwithacompositionalhierarchicalmodel AT alesleonardis symchmanunsupervisedapproachforpatterndiscoveryinsymbolicmusicwithacompositionalhierarchicalmodel AT matijamarolt symchmanunsupervisedapproachforpatterndiscoveryinsymbolicmusicwithacompositionalhierarchicalmodel |