{"id":"https://openalex.org/W2398250449","doi":"https://doi.org/10.1109/icassp.2016.7471714","title":"Harmonic-percussive-residual sound separation using the structure tensor on spectrograms","display_name":"Harmonic-percussive-residual sound separation using the structure tensor on spectrograms","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398250449","doi":"https://doi.org/10.1109/icassp.2016.7471714","mag":"2398250449"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028689201","display_name":"Richard F\u00fcg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Richard Fug","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071040838","display_name":"Andreas Niedermeier","orcid":"https://orcid.org/0000-0003-4744-3725"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Niedermeier","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057320374","display_name":"Jonathan Driedger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Driedger","raw_affiliation_strings":["International Audio Laboratories Erlangen"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034297652","display_name":"Sascha Disch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sascha Disch","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany","International Audio Laboratories Erlangen"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard Muller","raw_affiliation_strings":["International Audio Laboratories Erlangen"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028689201"],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7037037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"445","last_page":"449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994999766349792,"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/spectrogram","display_name":"Spectrogram","score":0.924108624458313},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.8117972612380981},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.6501352190971375},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5743880271911621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5538972020149231},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4851185083389282},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.48318377137184143},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4797550439834595},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.46621590852737427},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4522831439971924},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.4340018630027771},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4320123791694641},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.43061119318008423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3790598213672638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34419888257980347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28804898262023926},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24261179566383362},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.21116206049919128},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17472097277641296},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.149210125207901},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.1326451599597931},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09220072627067566},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.07278108596801758}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.924108624458313},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8117972612380981},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.6501352190971375},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5743880271911621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5538972020149231},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4851185083389282},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.48318377137184143},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4797550439834595},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.46621590852737427},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4522831439971924},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.4340018630027771},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4320123791694641},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.43061119318008423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3790598213672638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34419888257980347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28804898262023926},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24261179566383362},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.21116206049919128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17472097277641296},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.149210125207901},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.1326451599597931},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09220072627067566},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.07278108596801758},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7471714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/394824","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/394824","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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W141230911","https://openalex.org/W1491742974","https://openalex.org/W1498858047","https://openalex.org/W1542873368","https://openalex.org/W1545934923","https://openalex.org/W1561135842","https://openalex.org/W2007664495","https://openalex.org/W2036405930","https://openalex.org/W2075483674","https://openalex.org/W2100772705","https://openalex.org/W2111308925","https://openalex.org/W2118159075","https://openalex.org/W2126264921","https://openalex.org/W2127851351","https://openalex.org/W2127884536","https://openalex.org/W2162499636","https://openalex.org/W2208082420","https://openalex.org/W2403405926","https://openalex.org/W2407513162"],"related_works":["https://openalex.org/W1889291648","https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2098101267","https://openalex.org/W2898606530","https://openalex.org/W335396218","https://openalex.org/W2533590149","https://openalex.org/W2059119686"],"abstract_inverted_index":{"Harmonic-percussive-residual":[0],"(HPR)":[1],"sound":[2],"separation":[3],"is":[4,92],"a":[5,27,59,85,114],"useful":[6],"preprocessing":[7],"tool":[8,124],"for":[9,68,94],"applications":[10],"such":[11],"as":[12,178,180],"pitched":[13],"instrument":[14],"transcription":[15],"or":[16],"rhythm":[17],"extraction.":[18],"Recent":[19],"methods":[20,45],"rely":[21],"on":[22],"the":[23,106,120,134,157,166],"observation":[24],"that":[25,48,74,117],"in":[26,133,156],"spectrogram":[28],"representation,":[29],"harmonic":[30],"sounds":[31,38],"lead":[32,39,99],"to":[33,40,100,146],"horizontal":[34,51,89],"structures":[35,47],"and":[36,90,97,151],"percussive":[37],"vertical":[41,53,91],"structures.":[42],"Furthermore,":[43],"these":[44,95],"associate":[46],"are":[49],"neither":[50],"nor":[52],"(i.e.,":[54],"non-harmonic,":[55],"non-percussive":[56],"sounds)":[57],"with":[58],"residual":[60,107,152],"category.":[61],"However,":[62],"this":[63,110,140],"assumption":[64],"does":[65],"not":[66],"hold":[67],"signals":[69,96],"like":[70],"frequency":[71,160],"modulated":[72,161],"tones":[73],"show":[75,138],"fluctuating":[76],"spectral":[77],"structures,":[78],"while":[79],"nevertheless":[80],"carrying":[81],"tonal":[82,103],"information.":[83],"Therefore,":[84],"strict":[86],"classification":[87],"into":[88,105],"inappropriate":[93],"might":[98],"leakage":[101],"of":[102,159,168,173],"information":[104,142],"component.":[108],"In":[109],"work,":[111],"we":[112,164],"propose":[113],"novel":[115],"method":[116,170],"instead":[118],"uses":[119],"structure":[121],"tensor\u2014a":[122],"mathematical":[123],"known":[125],"from":[126],"image":[127],"processing\u2014to":[128],"calculate":[129],"predominant":[130],"orientation":[131,141],"angles":[132],"magnitude":[135],"spectrogram.":[136],"We":[137],"how":[139],"can":[143],"be":[144],"used":[145],"distinguish":[147],"between":[148],"harmonic,":[149],"percussive,":[150],"signal":[153],"components,":[154],"even":[155],"case":[158],"signals.":[162],"Finally,":[163],"verify":[165],"effectiveness":[167],"our":[169],"by":[171],"means":[172],"both":[174],"objective":[175],"evaluation":[176],"measures":[177],"well":[179],"audio":[181],"examples.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}