Automatic Music Summarization. A "Thumbnail" Approach
Identifieur interne : 000023 ( Main/Exploration ); précédent : 000022; suivant : 000024Automatic Music Summarization. A "Thumbnail" Approach
Auteurs : Jakub Głaczy Ski [Pologne] ; Ewa Łukasik [Pologne]Source :
- Archives of Acoustics [ 0137-5075 ] ; 2011-05-01.
English descriptors
- KwdEn :
- Teeft :
- Aggregated, Aggregated similarity, Algorithm, Audio, Audio domain, Automatic music, Automatic music summarization, Average score, Chorus repetitions, Coherence, Consecutive frames, Convention paper, Cosine distance, Descriptive comments, Distance measure, Entire music piece, Entire piece, Entire song, Experimental evaluation, Feature vectors, Foote, Great deal, Ieee icassp, Individual criteria, Long fragment, Matrix, Maximum summary score, Music information retrieval, Music piece, Music retrieval, Music summary, Music thumbnail, Musical phrase, Musical piece, Musical work, Optimal summary, Overall quality, Parameters vector, Polyphonic music, Popular music, Proc, Professional musicians, Representative part, Retrieval, Rondo alla turca, Scalar product, Semantic information, Signal analysis, Similarity, Similarity matrix, Similarity measure, Similarity value, Solo guitar, Standard deviation, Subjective assessment, Summarization, Summary score, Tchebyshev, Tchebyshev distance, Tchebyshev distance measure, Thumbnail, Thumbnail choice, Thumbnail extraction, Thumbnail generation, Ukasik.
Abstract
In the paper, various approaches to automatic music audio summarization are discussed. The project described in detail, is the realization of a method for extracting a music thumbnail - a fragment of continuous music of a given duration time that is most similar to the entire music piece. The results of subjective assessment of the thumbnail choice are presented, where four parameters have been taken into account: clarity (representation of the essence of the piece of music), conciseness (the motifs are not repeated in the summary), coherence of music structure, and overall quality of summary usefulness.
Url:
DOI: 10.2478/v10168-011-0023-y
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Automatic Music Summarization. A "Thumbnail" Approach</title><author><name sortKey="Glaczy Ski, Jakub" sort="Glaczy Ski, Jakub" uniqKey="Glaczy Ski J" first="Jakub" last="Głaczy Ski">Jakub Głaczy Ski</name></author><author><name sortKey="Lukasik, Ewa" sort="Lukasik, Ewa" uniqKey="Lukasik E" first="Ewa" last="Łukasik">Ewa Łukasik</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:82F41C950EFC9DA717BE1F1456616749109CD356</idno><date when="2011" year="2011">2011</date><idno type="doi">10.2478/v10168-011-0023-y</idno><idno type="url">https://api.istex.fr/document/82F41C950EFC9DA717BE1F1456616749109CD356/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000269</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000269</idno><idno type="wicri:Area/Main/Curation">000267</idno><idno type="wicri:Area/Main/Exploration">000023</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Exploration">000023</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Automatic Music Summarization. A "Thumbnail" Approach</title><author><name sortKey="Glaczy Ski, Jakub" sort="Glaczy Ski, Jakub" uniqKey="Glaczy Ski J" first="Jakub" last="Głaczy Ski">Jakub Głaczy Ski</name><affiliation wicri:level="1"><country xml:lang="fr">Pologne</country><wicri:regionArea>Faculty of Computing Science, Institute of Computing Science, Poznań University of Technology, Piotrowo 3A, 60-965 Poznań</wicri:regionArea><wicri:noRegion>60-965 Poznań</wicri:noRegion></affiliation><affiliation wicri:level="1"><country xml:lang="fr">Pologne</country><wicri:regionArea>Faculty of Computing Science, Institute of Computing Science, Poznań University of Technology, Piotrowo 3A, 60-965 Poznań</wicri:regionArea><wicri:noRegion>60-965 Poznań</wicri:noRegion></affiliation></author><author><name sortKey="Lukasik, Ewa" sort="Lukasik, Ewa" uniqKey="Lukasik E" first="Ewa" last="Łukasik">Ewa Łukasik</name><affiliation wicri:level="1"><country xml:lang="fr">Pologne</country><wicri:regionArea>Faculty of Computing Science, Institute of Computing Science, Poznań University of Technology, Piotrowo 3A, 60-965 Poznań</wicri:regionArea><wicri:noRegion>60-965 Poznań</wicri:noRegion></affiliation><affiliation wicri:level="1"><country xml:lang="fr">Pologne</country><wicri:regionArea>Faculty of Computing Science, Institute of Computing Science, Poznań University of Technology, Piotrowo 3A, 60-965 Poznań</wicri:regionArea><wicri:noRegion>60-965 Poznań</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Archives of Acoustics</title><idno type="ISSN">0137-5075</idno><imprint><publisher>Versita</publisher><date type="published" when="2011-05-01">2011-05-01</date><biblScope unit="volume">36</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="297">297</biblScope><biblScope unit="page" to="309">309</biblScope></imprint><idno type="ISSN">0137-5075</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0137-5075</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Music Information Retrieval</term><term>automatic music summarization</term><term>automatic music transcription</term><term>key phrases</term><term>music thumbnail</term></keywords><keywords scheme="Teeft" xml:lang="en"><term>Aggregated</term><term>Aggregated similarity</term><term>Algorithm</term><term>Audio</term><term>Audio domain</term><term>Automatic music</term><term>Automatic music summarization</term><term>Average score</term><term>Chorus repetitions</term><term>Coherence</term><term>Consecutive frames</term><term>Convention paper</term><term>Cosine distance</term><term>Descriptive comments</term><term>Distance measure</term><term>Entire music piece</term><term>Entire piece</term><term>Entire song</term><term>Experimental evaluation</term><term>Feature vectors</term><term>Foote</term><term>Great deal</term><term>Ieee icassp</term><term>Individual criteria</term><term>Long fragment</term><term>Matrix</term><term>Maximum summary score</term><term>Music information retrieval</term><term>Music piece</term><term>Music retrieval</term><term>Music summary</term><term>Music thumbnail</term><term>Musical phrase</term><term>Musical piece</term><term>Musical work</term><term>Optimal summary</term><term>Overall quality</term><term>Parameters vector</term><term>Polyphonic music</term><term>Popular music</term><term>Proc</term><term>Professional musicians</term><term>Representative part</term><term>Retrieval</term><term>Rondo alla turca</term><term>Scalar product</term><term>Semantic information</term><term>Signal analysis</term><term>Similarity</term><term>Similarity matrix</term><term>Similarity measure</term><term>Similarity value</term><term>Solo guitar</term><term>Standard deviation</term><term>Subjective assessment</term><term>Summarization</term><term>Summary score</term><term>Tchebyshev</term><term>Tchebyshev distance</term><term>Tchebyshev distance measure</term><term>Thumbnail</term><term>Thumbnail choice</term><term>Thumbnail extraction</term><term>Thumbnail generation</term><term>Ukasik</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In the paper, various approaches to automatic music audio summarization are discussed. The project described in detail, is the realization of a method for extracting a music thumbnail - a fragment of continuous music of a given duration time that is most similar to the entire music piece. The results of subjective assessment of the thumbnail choice are presented, where four parameters have been taken into account: clarity (representation of the essence of the piece of music), conciseness (the motifs are not repeated in the summary), coherence of music structure, and overall quality of summary usefulness.</div></front></TEI><affiliations><list><country><li>Pologne</li></country></list><tree><country name="Pologne"><noRegion><name sortKey="Glaczy Ski, Jakub" sort="Glaczy Ski, Jakub" uniqKey="Glaczy Ski J" first="Jakub" last="Głaczy Ski">Jakub Głaczy Ski</name></noRegion><name sortKey="Glaczy Ski, Jakub" sort="Glaczy Ski, Jakub" uniqKey="Glaczy Ski J" first="Jakub" last="Głaczy Ski">Jakub Głaczy Ski</name><name sortKey="Lukasik, Ewa" sort="Lukasik, Ewa" uniqKey="Lukasik E" first="Ewa" last="Łukasik">Ewa Łukasik</name><name sortKey="Lukasik, Ewa" sort="Lukasik, Ewa" uniqKey="Lukasik E" first="Ewa" last="Łukasik">Ewa Łukasik</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/DiesIraeV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000023 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000023 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= DiesIraeV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:82F41C950EFC9DA717BE1F1456616749109CD356
|texte= Automatic Music Summarization. A "Thumbnail" Approach
}}
| This area was generated with Dilib version V0.6.33. |  |