{"id":"https://openalex.org/W2153039158","doi":"https://doi.org/10.1109/tasl.2009.2025099","title":"Audio Signal Representations for Indexing in the Transform Domain","display_name":"Audio Signal Representations for Indexing in the Transform Domain","publication_year":2010,"publication_date":"2010-02-16","ids":{"openalex":"https://openalex.org/W2153039158","doi":"https://doi.org/10.1109/tasl.2009.2025099","mag":"2153039158"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2025099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2025099","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5036973211","display_name":"Emmanuel Ravelli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133716","display_name":"Institut Jean Le Rond d'Alembert","ror":"https://ror.org/043we9s22","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210095849","https://openalex.org/I4210133716"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Ravelli","raw_affiliation_strings":["Institut Jean le Rond d'Alembert-LAM, Universit\u00e9 Pierre et Marie Curie, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Jean le Rond d'Alembert-LAM, Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I4210133716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["Institut Telecom, Telecom ParisTech, CNRS-LTCI, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Telecom, Telecom ParisTech, CNRS-LTCI, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058259063","display_name":"Laurent Daudet","orcid":"https://orcid.org/0000-0001-5811-1078"},"institutions":[{"id":"https://openalex.org/I4210133716","display_name":"Institut Jean Le Rond d'Alembert","ror":"https://ror.org/043we9s22","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210095849","https://openalex.org/I4210133716"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Daudet","raw_affiliation_strings":["Institut Jean le Rond d'Alembert-LAM, Universit\u00e9 Pierre et Marie Curie, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Jean le Rond d'Alembert-LAM, Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I4210133716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7567,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96729328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"3","first_page":"434","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/codec","display_name":"Codec","score":0.7929362654685974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891228199005127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6131204962730408},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.54640793800354},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5259948968887329},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5258919596672058},{"id":"https://openalex.org/keywords/dynamic-range-compression","display_name":"Dynamic range compression","score":0.5240278840065002},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5237269997596741},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.514202356338501},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5137866139411926},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5122033953666687},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.45018139481544495},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41775578260421753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39120855927467346},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3443852961063385},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.28724467754364014},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.10460352897644043},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10125380754470825},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08417275547981262},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0679575502872467}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7929362654685974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891228199005127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6131204962730408},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.54640793800354},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5259948968887329},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5258919596672058},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.5240278840065002},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5237269997596741},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.514202356338501},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5137866139411926},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5122033953666687},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.45018139481544495},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41775578260421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39120855927467346},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3443852961063385},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.28724467754364014},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.10460352897644043},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10125380754470825},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08417275547981262},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0679575502872467}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2009.2025099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2025099","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G926750160","display_name":"D\u00e9composition en El\u00e9ments Sonores et Applications Musicales","funder_award_id":"ANR-06-JCJC-0027","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W98493776","https://openalex.org/W152909648","https://openalex.org/W1503560067","https://openalex.org/W1542377715","https://openalex.org/W1861596447","https://openalex.org/W1970704574","https://openalex.org/W1999949665","https://openalex.org/W2013025417","https://openalex.org/W2044637901","https://openalex.org/W2067063915","https://openalex.org/W2070210210","https://openalex.org/W2095725796","https://openalex.org/W2096425727","https://openalex.org/W2103076542","https://openalex.org/W2104352833","https://openalex.org/W2106992993","https://openalex.org/W2111007352","https://openalex.org/W2117647820","https://openalex.org/W2123577100","https://openalex.org/W2133824856","https://openalex.org/W2139238328","https://openalex.org/W2148154194","https://openalex.org/W2155764689","https://openalex.org/W2166248431","https://openalex.org/W2166435644","https://openalex.org/W2167455298","https://openalex.org/W2167969117","https://openalex.org/W4256516878","https://openalex.org/W6603977465","https://openalex.org/W6630180946","https://openalex.org/W6632405293","https://openalex.org/W6639065442","https://openalex.org/W6674700200","https://openalex.org/W6676368125","https://openalex.org/W6678448728","https://openalex.org/W6684426571"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W3135871143","https://openalex.org/W2772926198","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W2020966186","https://openalex.org/W296599067","https://openalex.org/W2898469868","https://openalex.org/W2119339729","https://openalex.org/W4382560817"],"abstract_inverted_index":{"Indexing":[0],"audio":[1,47,83,107,112,134],"signals":[2,23],"directly":[3],"in":[4,25,44,76,144],"the":[5,35,41,137],"transform":[6,91],"domain":[7],"can":[8],"potentially":[9],"save":[10],"a":[11,19,26,59,68,80,87,93],"significant":[12],"amount":[13],"of":[14,22,146],"computation":[15,149],"when":[16],"working":[17],"on":[18,86],"large":[20],"database":[21],"stored":[24],"lossy":[27],"compression":[28],"format,":[29],"without":[30],"having":[31],"to":[32],"fully":[33],"decode":[34],"signals.":[36],"Here,":[37],"we":[38],"show":[39,103],"that":[40,104],"representations":[42],"used":[43],"standard":[45,139],"transform-based":[46],"codecs":[48],"(e.g.,":[49],"MDCT":[50,90],"for":[51,56,63,97,114],"AAC,":[52],"or":[53],"hybrid":[54],"PQF/MDCT":[55],"MP3)":[57],"have":[58],"sufficient":[60],"time":[61],"resolution":[62,95],"some":[64],"rhythmic":[65],"features,":[66],"but":[67],"poor":[69],"frequency":[70],"resolution,":[71],"which":[72],"prevents":[73],"their":[74],"use":[75],"tonality-related":[77],"applications.":[78],"Alternatively,":[79],"recently":[81],"developed":[82],"codec":[84,108,135],"based":[85],"sparse":[88],"multi-scale":[89],"has":[92],"good":[94],"both":[96],"time-":[98],"and":[99,123,136,141,148],"frequency-domain":[100],"features.":[101],"We":[102,127],"this":[105,132],"new":[106,133],"allows":[109],"efficient":[110],"transform-domain":[111],"indexing":[113],"three":[115],"different":[116],"applications,":[117],"namely":[118],"beat":[119],"tracking,":[120],"chord":[121],"recognition,":[122],"musical":[124],"genre":[125],"classification.":[126],"compare":[128],"results":[129],"obtained":[130],"with":[131],"two":[138],"MP3":[140],"AAC":[142],"codecs,":[143],"terms":[145],"performance":[147],"time.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}
