Deep learning-based automatic downbeat tracking: a brief review View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-12

AUTHORS

Bijue Jia, Jiancheng Lv, Dayiheng Liu

ABSTRACT

As an important format of multimedia, music has filled almost everyone’s life. Automatic analyzing of music is a significant step to satisfy people’s need for music retrieval and music recommendation in an effortless way. Thereinto, downbeat tracking has been a fundamental and continuous problem in Music Information Retrieval (MIR) area. Despite significant research efforts, downbeat tracking still remains a challenge. Previous researches either focus on feature engineering (extracting certain features by signal processing, which are semi-automatic solutions); or have some limitations: they can only model music audio recordings within limited time signatures and tempo ranges. Recently, deep learning has surpassed traditional machine learning methods and has become the primary algorithm in feature learning; the combination of traditional and deep learning methods also has made better performance. In this paper, we begin with a background introduction of downbeat tracking problem. Then, we give detailed discussions of the following topics: system architecture, feature extraction, deep neural network algorithms, data sets, and evaluation strategy. In addition, we take a look at the results from the annual benchmark evaluation—Music Information Retrieval Evaluation eXchange—as well as the developments in software implementations. Although much has been achieved in the area of automatic downbeat tracking, some problems still remain. We point out these problems and conclude with possible directions and challenges for future research. More... »

PAGES

1-22

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00530-019-00607-x

DOI

http://dx.doi.org/10.1007/s00530-019-00607-x

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112703108


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Sichuan University", 
          "id": "https://www.grid.ac/institutes/grid.13291.38", 
          "name": [
            "College of Computer Science, Sichuan University, Chengdu, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jia", 
        "givenName": "Bijue", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Sichuan University", 
          "id": "https://www.grid.ac/institutes/grid.13291.38", 
          "name": [
            "College of Computer Science, Sichuan University, Chengdu, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lv", 
        "givenName": "Jiancheng", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Sichuan University", 
          "id": "https://www.grid.ac/institutes/grid.13291.38", 
          "name": [
            "College of Computer Science, Sichuan University, Chengdu, People\u2019s Republic of China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Liu", 
        "givenName": "Dayiheng", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1002/aris.1440370108", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012485299"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/09298215.2013.879902", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017843626"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/323533a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018367015", 
          "https://doi.org/10.1038/323533a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0167-6393(98)00076-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021134317"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2647868.2654915", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025411302"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2647868.2654940", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026130486"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2502081.2502229", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026586955"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/192593.192700", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028424791"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-662-45402-2_151", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032084517", 
          "https://doi.org/10.1007/978-3-662-45402-2_151"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/0096-1523.30.5.956", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034899849"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00530-015-0485-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036492424", 
          "https://doi.org/10.1007/s00530-015-0485-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-21945-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036760936", 
          "https://doi.org/10.1007/978-3-319-21945-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-21945-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036760936", 
          "https://doi.org/10.1007/978-3-319-21945-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1037/a0013482", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037101958"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1997.9.8.1735", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038140272"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1525/mp.2003.20.4.431", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038246338"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2964284.2964308", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038414366"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-42294-7_28", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041126635", 
          "https://doi.org/10.1007/978-3-319-42294-7_28"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1250/ast.29.247", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042378264"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2013.10.021", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048603431"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/09298210701653310", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048645821"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2964284.2973795", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049612675"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-13287-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049912148", 
          "https://doi.org/10.1007/978-3-642-13287-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-13287-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049912148", 
          "https://doi.org/10.1007/978-3-642-13287-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-24797-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050223513", 
          "https://doi.org/10.1007/978-3-642-24797-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-24797-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050223513", 
          "https://doi.org/10.1007/978-3-642-24797-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1076/jnmr.30.2.159.7114", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051083474"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1017/s026114301000067x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053780321"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.667881", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061156743"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jproc.2008.916370", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061296941"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/mmul.2006.3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061409997"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2010.2045236", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516528"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2010.2098869", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516685"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tasl.2010.2098870", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061516686"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2015.2409737", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517454"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2016.2533858", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517718"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2016.2598305", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517857"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/taslp.2016.2623565", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061517915"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tmm.2014.2310701", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061698301"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsa.2002.800560", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061786085"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsa.2005.854090", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061786374"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsa.2005.858509", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061786451"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1155/s1110865704408099", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1063208076", 
          "https://doi.org/10.1155/s1110865704408099"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.17743/jaes.2016.0025", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068448289"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icnn.1988.23914", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086175414"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00530-017-0559-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090954889", 
          "https://doi.org/10.1007/s00530-017-0559-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00530-017-0559-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090954889", 
          "https://doi.org/10.1007/s00530-017-0559-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2012.6287906", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093340668"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ism.2015.126", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093614310"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2014.6854950", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093627962"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2014.6854598", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094046134"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2016.7471684", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094089853"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/asru.2015.7404790", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094465017"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2015.7178001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094631184"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/aspaa.2005.1540221", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095277417"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2012.6287912", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095375228"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/asru.2013.6707749", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095431288"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2014.6854177", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095598066"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/p16-1101", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099113537"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.25080/majora-7b98e3ed-003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1108066643"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03-12", 
    "datePublishedReg": "2019-03-12", 
    "description": "As an important format of multimedia, music has filled almost everyone\u2019s life. Automatic analyzing of music is a significant step to satisfy people\u2019s need for music retrieval and music recommendation in an effortless way. Thereinto, downbeat tracking has been a fundamental and continuous problem in Music Information Retrieval (MIR) area. Despite significant research efforts, downbeat tracking still remains a challenge. Previous researches either focus on feature engineering (extracting certain features by signal processing, which are semi-automatic solutions); or have some limitations: they can only model music audio recordings within limited time signatures and tempo ranges. Recently, deep learning has surpassed traditional machine learning methods and has become the primary algorithm in feature learning; the combination of traditional and deep learning methods also has made better performance. In this paper, we begin with a background introduction of downbeat tracking problem. Then, we give detailed discussions of the following topics: system architecture, feature extraction, deep neural network algorithms, data sets, and evaluation strategy. In addition, we take a look at the results from the annual benchmark evaluation\u2014Music Information Retrieval Evaluation eXchange\u2014as well as the developments in software implementations. Although much has been achieved in the area of automatic downbeat tracking, some problems still remain. We point out these problems and conclude with possible directions and challenges for future research.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00530-019-00607-x", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1284647", 
        "issn": [
          "0942-4962", 
          "1432-1882"
        ], 
        "name": "Multimedia Systems", 
        "type": "Periodical"
      }
    ], 
    "name": "Deep learning-based automatic downbeat tracking: a brief review", 
    "pagination": "1-22", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "af970cafbd296c505640d6262ebd5a2915fa966bd8b37f8b9e8a9927321f4bd5"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00530-019-00607-x"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112703108"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00530-019-00607-x", 
      "https://app.dimensions.ai/details/publication/pub.1112703108"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T11:38", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000358_0000000358/records_127432_00000011.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00530-019-00607-x"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s00530-019-00607-x'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s00530-019-00607-x'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00530-019-00607-x'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00530-019-00607-x'


 

This table displays all metadata directly associated to this object as RDF triples.

243 TRIPLES      21 PREDICATES      80 URIs      16 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00530-019-00607-x schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nf9626b453b344cbe98bde54c41ae7007
4 schema:citation sg:pub.10.1007/978-3-319-21945-5
5 sg:pub.10.1007/978-3-319-42294-7_28
6 sg:pub.10.1007/978-3-642-13287-2
7 sg:pub.10.1007/978-3-642-24797-2
8 sg:pub.10.1007/978-3-662-45402-2_151
9 sg:pub.10.1007/s00530-015-0485-2
10 sg:pub.10.1007/s00530-017-0559-4
11 sg:pub.10.1038/323533a0
12 sg:pub.10.1155/s1110865704408099
13 https://doi.org/10.1002/aris.1440370108
14 https://doi.org/10.1016/j.patrec.2013.10.021
15 https://doi.org/10.1016/s0167-6393(98)00076-4
16 https://doi.org/10.1017/s026114301000067x
17 https://doi.org/10.1037/0096-1523.30.5.956
18 https://doi.org/10.1037/a0013482
19 https://doi.org/10.1076/jnmr.30.2.159.7114
20 https://doi.org/10.1080/09298210701653310
21 https://doi.org/10.1080/09298215.2013.879902
22 https://doi.org/10.1109/34.667881
23 https://doi.org/10.1109/aspaa.2005.1540221
24 https://doi.org/10.1109/asru.2013.6707749
25 https://doi.org/10.1109/asru.2015.7404790
26 https://doi.org/10.1109/icassp.2012.6287906
27 https://doi.org/10.1109/icassp.2012.6287912
28 https://doi.org/10.1109/icassp.2014.6854177
29 https://doi.org/10.1109/icassp.2014.6854598
30 https://doi.org/10.1109/icassp.2014.6854950
31 https://doi.org/10.1109/icassp.2015.7178001
32 https://doi.org/10.1109/icassp.2016.7471684
33 https://doi.org/10.1109/icnn.1988.23914
34 https://doi.org/10.1109/ism.2015.126
35 https://doi.org/10.1109/jproc.2008.916370
36 https://doi.org/10.1109/mmul.2006.3
37 https://doi.org/10.1109/tasl.2010.2045236
38 https://doi.org/10.1109/tasl.2010.2098869
39 https://doi.org/10.1109/tasl.2010.2098870
40 https://doi.org/10.1109/taslp.2015.2409737
41 https://doi.org/10.1109/taslp.2016.2533858
42 https://doi.org/10.1109/taslp.2016.2598305
43 https://doi.org/10.1109/taslp.2016.2623565
44 https://doi.org/10.1109/tmm.2014.2310701
45 https://doi.org/10.1109/tsa.2002.800560
46 https://doi.org/10.1109/tsa.2005.854090
47 https://doi.org/10.1109/tsa.2005.858509
48 https://doi.org/10.1145/192593.192700
49 https://doi.org/10.1145/2502081.2502229
50 https://doi.org/10.1145/2647868.2654915
51 https://doi.org/10.1145/2647868.2654940
52 https://doi.org/10.1145/2964284.2964308
53 https://doi.org/10.1145/2964284.2973795
54 https://doi.org/10.1162/neco.1997.9.8.1735
55 https://doi.org/10.1250/ast.29.247
56 https://doi.org/10.1525/mp.2003.20.4.431
57 https://doi.org/10.17743/jaes.2016.0025
58 https://doi.org/10.18653/v1/p16-1101
59 https://doi.org/10.25080/majora-7b98e3ed-003
60 schema:datePublished 2019-03-12
61 schema:datePublishedReg 2019-03-12
62 schema:description As an important format of multimedia, music has filled almost everyone’s life. Automatic analyzing of music is a significant step to satisfy people’s need for music retrieval and music recommendation in an effortless way. Thereinto, downbeat tracking has been a fundamental and continuous problem in Music Information Retrieval (MIR) area. Despite significant research efforts, downbeat tracking still remains a challenge. Previous researches either focus on feature engineering (extracting certain features by signal processing, which are semi-automatic solutions); or have some limitations: they can only model music audio recordings within limited time signatures and tempo ranges. Recently, deep learning has surpassed traditional machine learning methods and has become the primary algorithm in feature learning; the combination of traditional and deep learning methods also has made better performance. In this paper, we begin with a background introduction of downbeat tracking problem. Then, we give detailed discussions of the following topics: system architecture, feature extraction, deep neural network algorithms, data sets, and evaluation strategy. In addition, we take a look at the results from the annual benchmark evaluation—Music Information Retrieval Evaluation eXchange—as well as the developments in software implementations. Although much has been achieved in the area of automatic downbeat tracking, some problems still remain. We point out these problems and conclude with possible directions and challenges for future research.
63 schema:genre research_article
64 schema:inLanguage en
65 schema:isAccessibleForFree false
66 schema:isPartOf sg:journal.1284647
67 schema:name Deep learning-based automatic downbeat tracking: a brief review
68 schema:pagination 1-22
69 schema:productId N1e309b21bfb940a1882eb89ba4ad6097
70 N5169e0c6bc2d48ab87ac95e9586e4a35
71 Nec3113deeb2c4330bf97e50318a64d3e
72 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112703108
73 https://doi.org/10.1007/s00530-019-00607-x
74 schema:sdDatePublished 2019-04-11T11:38
75 schema:sdLicense https://scigraph.springernature.com/explorer/license/
76 schema:sdPublisher N22c70bb5799045fd81a8edcb71b6e589
77 schema:url https://link.springer.com/10.1007%2Fs00530-019-00607-x
78 sgo:license sg:explorer/license/
79 sgo:sdDataset articles
80 rdf:type schema:ScholarlyArticle
81 N1e309b21bfb940a1882eb89ba4ad6097 schema:name dimensions_id
82 schema:value pub.1112703108
83 rdf:type schema:PropertyValue
84 N22c70bb5799045fd81a8edcb71b6e589 schema:name Springer Nature - SN SciGraph project
85 rdf:type schema:Organization
86 N5169e0c6bc2d48ab87ac95e9586e4a35 schema:name doi
87 schema:value 10.1007/s00530-019-00607-x
88 rdf:type schema:PropertyValue
89 N7f145a20132a427da23f19c995d6f69c schema:affiliation https://www.grid.ac/institutes/grid.13291.38
90 schema:familyName Liu
91 schema:givenName Dayiheng
92 rdf:type schema:Person
93 Na5956cdf31e54309b49ba88851d15679 rdf:first N7f145a20132a427da23f19c995d6f69c
94 rdf:rest rdf:nil
95 Nb60ae931de084312bd8fb2daff253266 schema:affiliation https://www.grid.ac/institutes/grid.13291.38
96 schema:familyName Lv
97 schema:givenName Jiancheng
98 rdf:type schema:Person
99 Ne8a2d0fce63e4e4c9f89b3556d84eee9 schema:affiliation https://www.grid.ac/institutes/grid.13291.38
100 schema:familyName Jia
101 schema:givenName Bijue
102 rdf:type schema:Person
103 Nec3113deeb2c4330bf97e50318a64d3e schema:name readcube_id
104 schema:value af970cafbd296c505640d6262ebd5a2915fa966bd8b37f8b9e8a9927321f4bd5
105 rdf:type schema:PropertyValue
106 Nf1f3eaaee8de4fa391c7e7a798228c43 rdf:first Nb60ae931de084312bd8fb2daff253266
107 rdf:rest Na5956cdf31e54309b49ba88851d15679
108 Nf9626b453b344cbe98bde54c41ae7007 rdf:first Ne8a2d0fce63e4e4c9f89b3556d84eee9
109 rdf:rest Nf1f3eaaee8de4fa391c7e7a798228c43
110 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
111 schema:name Information and Computing Sciences
112 rdf:type schema:DefinedTerm
113 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
114 schema:name Artificial Intelligence and Image Processing
115 rdf:type schema:DefinedTerm
116 sg:journal.1284647 schema:issn 0942-4962
117 1432-1882
118 schema:name Multimedia Systems
119 rdf:type schema:Periodical
120 sg:pub.10.1007/978-3-319-21945-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036760936
121 https://doi.org/10.1007/978-3-319-21945-5
122 rdf:type schema:CreativeWork
123 sg:pub.10.1007/978-3-319-42294-7_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041126635
124 https://doi.org/10.1007/978-3-319-42294-7_28
125 rdf:type schema:CreativeWork
126 sg:pub.10.1007/978-3-642-13287-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049912148
127 https://doi.org/10.1007/978-3-642-13287-2
128 rdf:type schema:CreativeWork
129 sg:pub.10.1007/978-3-642-24797-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050223513
130 https://doi.org/10.1007/978-3-642-24797-2
131 rdf:type schema:CreativeWork
132 sg:pub.10.1007/978-3-662-45402-2_151 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032084517
133 https://doi.org/10.1007/978-3-662-45402-2_151
134 rdf:type schema:CreativeWork
135 sg:pub.10.1007/s00530-015-0485-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036492424
136 https://doi.org/10.1007/s00530-015-0485-2
137 rdf:type schema:CreativeWork
138 sg:pub.10.1007/s00530-017-0559-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090954889
139 https://doi.org/10.1007/s00530-017-0559-4
140 rdf:type schema:CreativeWork
141 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
142 https://doi.org/10.1038/323533a0
143 rdf:type schema:CreativeWork
144 sg:pub.10.1155/s1110865704408099 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063208076
145 https://doi.org/10.1155/s1110865704408099
146 rdf:type schema:CreativeWork
147 https://doi.org/10.1002/aris.1440370108 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012485299
148 rdf:type schema:CreativeWork
149 https://doi.org/10.1016/j.patrec.2013.10.021 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048603431
150 rdf:type schema:CreativeWork
151 https://doi.org/10.1016/s0167-6393(98)00076-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021134317
152 rdf:type schema:CreativeWork
153 https://doi.org/10.1017/s026114301000067x schema:sameAs https://app.dimensions.ai/details/publication/pub.1053780321
154 rdf:type schema:CreativeWork
155 https://doi.org/10.1037/0096-1523.30.5.956 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034899849
156 rdf:type schema:CreativeWork
157 https://doi.org/10.1037/a0013482 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037101958
158 rdf:type schema:CreativeWork
159 https://doi.org/10.1076/jnmr.30.2.159.7114 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051083474
160 rdf:type schema:CreativeWork
161 https://doi.org/10.1080/09298210701653310 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048645821
162 rdf:type schema:CreativeWork
163 https://doi.org/10.1080/09298215.2013.879902 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017843626
164 rdf:type schema:CreativeWork
165 https://doi.org/10.1109/34.667881 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061156743
166 rdf:type schema:CreativeWork
167 https://doi.org/10.1109/aspaa.2005.1540221 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095277417
168 rdf:type schema:CreativeWork
169 https://doi.org/10.1109/asru.2013.6707749 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095431288
170 rdf:type schema:CreativeWork
171 https://doi.org/10.1109/asru.2015.7404790 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094465017
172 rdf:type schema:CreativeWork
173 https://doi.org/10.1109/icassp.2012.6287906 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093340668
174 rdf:type schema:CreativeWork
175 https://doi.org/10.1109/icassp.2012.6287912 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095375228
176 rdf:type schema:CreativeWork
177 https://doi.org/10.1109/icassp.2014.6854177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095598066
178 rdf:type schema:CreativeWork
179 https://doi.org/10.1109/icassp.2014.6854598 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094046134
180 rdf:type schema:CreativeWork
181 https://doi.org/10.1109/icassp.2014.6854950 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093627962
182 rdf:type schema:CreativeWork
183 https://doi.org/10.1109/icassp.2015.7178001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094631184
184 rdf:type schema:CreativeWork
185 https://doi.org/10.1109/icassp.2016.7471684 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094089853
186 rdf:type schema:CreativeWork
187 https://doi.org/10.1109/icnn.1988.23914 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086175414
188 rdf:type schema:CreativeWork
189 https://doi.org/10.1109/ism.2015.126 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093614310
190 rdf:type schema:CreativeWork
191 https://doi.org/10.1109/jproc.2008.916370 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061296941
192 rdf:type schema:CreativeWork
193 https://doi.org/10.1109/mmul.2006.3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061409997
194 rdf:type schema:CreativeWork
195 https://doi.org/10.1109/tasl.2010.2045236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516528
196 rdf:type schema:CreativeWork
197 https://doi.org/10.1109/tasl.2010.2098869 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516685
198 rdf:type schema:CreativeWork
199 https://doi.org/10.1109/tasl.2010.2098870 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061516686
200 rdf:type schema:CreativeWork
201 https://doi.org/10.1109/taslp.2015.2409737 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517454
202 rdf:type schema:CreativeWork
203 https://doi.org/10.1109/taslp.2016.2533858 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517718
204 rdf:type schema:CreativeWork
205 https://doi.org/10.1109/taslp.2016.2598305 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517857
206 rdf:type schema:CreativeWork
207 https://doi.org/10.1109/taslp.2016.2623565 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061517915
208 rdf:type schema:CreativeWork
209 https://doi.org/10.1109/tmm.2014.2310701 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061698301
210 rdf:type schema:CreativeWork
211 https://doi.org/10.1109/tsa.2002.800560 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061786085
212 rdf:type schema:CreativeWork
213 https://doi.org/10.1109/tsa.2005.854090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061786374
214 rdf:type schema:CreativeWork
215 https://doi.org/10.1109/tsa.2005.858509 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061786451
216 rdf:type schema:CreativeWork
217 https://doi.org/10.1145/192593.192700 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028424791
218 rdf:type schema:CreativeWork
219 https://doi.org/10.1145/2502081.2502229 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026586955
220 rdf:type schema:CreativeWork
221 https://doi.org/10.1145/2647868.2654915 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025411302
222 rdf:type schema:CreativeWork
223 https://doi.org/10.1145/2647868.2654940 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026130486
224 rdf:type schema:CreativeWork
225 https://doi.org/10.1145/2964284.2964308 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038414366
226 rdf:type schema:CreativeWork
227 https://doi.org/10.1145/2964284.2973795 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049612675
228 rdf:type schema:CreativeWork
229 https://doi.org/10.1162/neco.1997.9.8.1735 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038140272
230 rdf:type schema:CreativeWork
231 https://doi.org/10.1250/ast.29.247 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042378264
232 rdf:type schema:CreativeWork
233 https://doi.org/10.1525/mp.2003.20.4.431 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038246338
234 rdf:type schema:CreativeWork
235 https://doi.org/10.17743/jaes.2016.0025 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068448289
236 rdf:type schema:CreativeWork
237 https://doi.org/10.18653/v1/p16-1101 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099113537
238 rdf:type schema:CreativeWork
239 https://doi.org/10.25080/majora-7b98e3ed-003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1108066643
240 rdf:type schema:CreativeWork
241 https://www.grid.ac/institutes/grid.13291.38 schema:alternateName Sichuan University
242 schema:name College of Computer Science, Sichuan University, Chengdu, People’s Republic of China
243 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...