{"id":"https://openalex.org/W4406317437","doi":"https://doi.org/10.1186/s13636-024-00390-2","title":"Sound recurrence analysis for acoustic scene classification","display_name":"Sound recurrence analysis for acoustic scene classification","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W4406317437","doi":"https://doi.org/10.1186/s13636-024-00390-2"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00390-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00390-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00390-2","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00390-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jakob Abe\u00dfer","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT, Ehrenbergstr. 31, 98693, Ilmenau, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4689-7944","affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ehrenbergstr. 31, 98693, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619209","display_name":"Zhiwei Liang","orcid":"https://orcid.org/0000-0002-4243-0354"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhiwei Liang","raw_affiliation_strings":["Audio Information Processing, TU M\u00fcnchen, Theresienstr. 90, 80333, M\u00fcnchen, Germany","Semantic Music Technologies, Fraunhofer IDMT, Ehrenbergstr. 31, 98693, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Information Processing, TU M\u00fcnchen, Theresienstr. 90, 80333, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ehrenbergstr. 31, 98693, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031783799","display_name":"Bernhard U. Seeber","orcid":"https://orcid.org/0000-0002-3621-3409"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernhard Seeber","raw_affiliation_strings":["Audio Information Processing, TU M\u00fcnchen, Theresienstr. 90, 80333, M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Information Processing, TU M\u00fcnchen, Theresienstr. 90, 80333, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047532715"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73325847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7845540046691895},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.7145782709121704},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6449447870254517},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.5794273614883423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.567776083946228},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.509334921836853},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5076287984848022},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49697473645210266},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.49073755741119385},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4296053349971771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28378334641456604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15103229880332947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845540046691895},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.7145782709121704},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6449447870254517},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.5794273614883423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.567776083946228},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.509334921836853},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5076287984848022},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49697473645210266},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.49073755741119385},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4296053349971771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28378334641456604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15103229880332947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-024-00390-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00390-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00390-2","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:40e18f7ff43d4b3c89bd67b215ba4116","is_oa":true,"landing_page_url":"https://doaj.org/article/40e18f7ff43d4b3c89bd67b215ba4116","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-15 (2025)","raw_type":"article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/481327","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/481327","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00390-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00390-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00390-2","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G3041439062","display_name":null,"funder_award_id":"AB 675/2-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3150295464","display_name":"Informierte Klangquellenerkennung in Musik und Audiosignalen","funder_award_id":"350953655","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3171909130","display_name":null,"funder_award_id":"news-polygraph (funding code 03RU2U151D)","funder_id":"https://openalex.org/F4320326494","funder_display_name":"Bundesministerium f\u00fcr Bildung, Wissenschaft, Forschung und Technologie"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320326494","display_name":"Bundesministerium f\u00fcr Bildung, Wissenschaft, Forschung und Technologie","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406317437.pdf","grobid_xml":"https://content.openalex.org/works/W4406317437.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1575910154","https://openalex.org/W2009354116","https://openalex.org/W2022668263","https://openalex.org/W2103235956","https://openalex.org/W2131739315","https://openalex.org/W2136738044","https://openalex.org/W2194775991","https://openalex.org/W2342655467","https://openalex.org/W2552850818","https://openalex.org/W2747230102","https://openalex.org/W2759976799","https://openalex.org/W2889309940","https://openalex.org/W2890718983","https://openalex.org/W2899201823","https://openalex.org/W2962711843","https://openalex.org/W2963881567","https://openalex.org/W2982415754","https://openalex.org/W3012504141","https://openalex.org/W3015530480","https://openalex.org/W3114232785","https://openalex.org/W3120041065","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4238292067","https://openalex.org/W4289792665","https://openalex.org/W4308931326","https://openalex.org/W4312654700","https://openalex.org/W4318831574","https://openalex.org/W4372341277","https://openalex.org/W4387068368","https://openalex.org/W4387865689","https://openalex.org/W4388117483","https://openalex.org/W6912594804"],"related_works":["https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W1988083194","https://openalex.org/W2282503792","https://openalex.org/W2970126706","https://openalex.org/W2365709658","https://openalex.org/W2747085439","https://openalex.org/W1562588264","https://openalex.org/W1593731728","https://openalex.org/W2770198033"],"abstract_inverted_index":{"Abstract":[0],"In":[1,48,70,117,171],"everyday":[2],"life,":[3],"people":[4],"experience":[5],"different":[6],"soundscapes":[7,43],"in":[8,32,41,150,163,213],"which":[9,178],"natural":[10,42],"sounds,":[11],"animal":[12],"noises,":[13],"and":[14,34,58,93,114,154,182],"man-made":[15],"sounds":[16,149],"blend":[17],"together.":[18],"Although":[19],"there":[20],"have":[21],"been":[22],"several":[23],"studies":[24],"on":[25,204],"the":[26,36,53,71,102,118,144,172,205,214],"importance":[27],"of":[28,38,56,74,105,147,152],"recurring":[29],"sound":[30,60,88,106,161,185,196],"patterns":[31,55,90],"music":[33],"language,":[35],"relevance":[37],"this":[39,49],"phenomenon":[40],"is":[44,79],"still":[45],"largely":[46],"unexplored.":[47],"article,":[50],"we":[51,121],"study":[52],"repetition":[54,89,112,146,197],"harmonic":[57,92,160],"transient":[59,94,148],"events":[61],"as":[62,108,110,129,157,159],"potential":[63],"cues":[64],"for":[65,140,191],"acoustic":[66,82,164,208],"scene":[67,83,165],"classification":[68],"(ASC).":[69],"first":[72],"part":[73],"our":[75,77],"study,":[76],"aim":[78],"to":[80,100,125,134,168,216],"identify":[81],"classes":[84,166,193],"that":[85],"exhibit":[86],"characteristic":[87,145],"concerning":[91],"sounds.":[95],"We":[96,142],"propose":[97],"three":[98,123],"metrics":[99],"measure":[101],"overall":[103],"prevalence":[104],"repetitions":[107,162],"well":[109,158],"their":[111,217],"periods":[113],"temporal":[115],"stability.":[116],"second":[119],"part,":[120],"evaluate":[122],"strategies":[124],"incorporate":[126],"self-similarity":[127],"matrices":[128],"an":[130],"additional":[131,202],"input":[132],"feature":[133],"a":[135],"convolutional":[136],"neural":[137],"network":[138,176],"architecture":[139],"ASC.":[141],"observe":[143],"recordings":[151],"\u201cpark\u201d":[153],"\u201cstreet":[155],"traffic\u201d":[156],"related":[167],"public":[169],"transportation.":[170],"ASC":[173],"experiments,":[174],"hybrid":[175],"architectures,":[177],"combine":[179],"spectrogram":[180],"features":[181,183],"from":[184],"recurrence":[186],"analysis,":[187],"show":[188],"increased":[189],"accuracy":[190],"those":[192],"with":[194],"prominent":[195],"patterns.":[198],"Our":[199],"findings":[200],"provide":[201],"perspective":[203],"distinctions":[206],"among":[207],"scenes":[209],"previously":[210],"primarily":[211],"ascribed":[212],"literature":[215],"spectral":[218],"features.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}