{"id":"https://openalex.org/W2549961504","doi":"https://doi.org/10.1109/mlsp.2016.7738904","title":"Scale and shift invariant time/frequency representation using auditory statistics: Application to rhythm description","display_name":"Scale and shift invariant time/frequency representation using auditory statistics: Application to rhythm description","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2549961504","doi":"https://doi.org/10.1109/mlsp.2016.7738904","mag":"2549961504"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2016.7738904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2016.7738904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024010752","display_name":"Ugo Marchand","orcid":null},"institutions":[{"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/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ugo Marchand","raw_affiliation_strings":["STMS IRCAM-CNRS-UPMC, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STMS IRCAM-CNRS-UPMC, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"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/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["STMS IRCAM-CNRS-UPMC, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STMS IRCAM-CNRS-UPMC, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6386,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92290634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.7346041202545166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6434222459793091},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5686817765235901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.562397837638855},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5610539317131042},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5469659566879272},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5395926237106323},{"id":"https://openalex.org/keywords/scale-invariance","display_name":"Scale invariance","score":0.43692445755004883},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42624717950820923},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.42042481899261475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3822711706161499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34211933612823486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2766849994659424},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23507460951805115},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1715255081653595},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16313177347183228},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10116451978683472}],"concepts":[{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.7346041202545166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434222459793091},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5686817765235901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.562397837638855},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5610539317131042},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5469659566879272},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5395926237106323},{"id":"https://openalex.org/C135593079","wikidata":"https://www.wikidata.org/wiki/Q1750766","display_name":"Scale invariance","level":2,"score":0.43692445755004883},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42624717950820923},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.42042481899261475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3822711706161499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34211933612823486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2766849994659424},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23507460951805115},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1715255081653595},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16313177347183228},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10116451978683472},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2016.7738904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2016.7738904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W56990984","https://openalex.org/W1501078361","https://openalex.org/W1721549435","https://openalex.org/W1832929414","https://openalex.org/W1984056834","https://openalex.org/W1998762829","https://openalex.org/W2017282333","https://openalex.org/W2018811756","https://openalex.org/W2037340080","https://openalex.org/W2052872069","https://openalex.org/W2062663442","https://openalex.org/W2098353298","https://openalex.org/W2103941300","https://openalex.org/W2107793170","https://openalex.org/W2121761475","https://openalex.org/W2128031217","https://openalex.org/W2129338995","https://openalex.org/W2130737746","https://openalex.org/W2133824856","https://openalex.org/W2140450582","https://openalex.org/W2149128427","https://openalex.org/W2178247676","https://openalex.org/W2294252515","https://openalex.org/W2295824129","https://openalex.org/W2582368719","https://openalex.org/W6602269247","https://openalex.org/W6629849291","https://openalex.org/W6697413020","https://openalex.org/W6697458653","https://openalex.org/W6732863995"],"related_works":["https://openalex.org/W2072492413","https://openalex.org/W2997159972","https://openalex.org/W4296378967","https://openalex.org/W2064134577","https://openalex.org/W2373995729","https://openalex.org/W3203096336","https://openalex.org/W2393707162","https://openalex.org/W2097033632","https://openalex.org/W2021783512","https://openalex.org/W2021670453"],"abstract_inverted_index":{"In":[0],"this":[1,86,106],"paper":[2],"we":[3,74,108],"propose":[4,109],"two":[5,111],"novel":[6,112],"scale":[7],"and":[8,155],"shift-invariant":[9],"time-frequency":[10],"representations":[11,37,147],"of":[12,25,67,133,151,164,171],"the":[13,23,35,52,59,64,68,77,80,93,96,120,124,130,137,140,162,172],"audio":[14,27,69,97],"content.":[15],"Scale-invariance":[16],"is":[17,117],"a":[18,149,168],"desired":[19],"property":[20,46],"to":[21,33,79,91,148],"describe":[22],"rhythm":[24,152],"an":[26],"signal":[28],"as":[29],"it":[30],"will":[31],"allow":[32,90],"obtain":[34],"same":[36,39],"for":[38,56],"rhythms":[40],"played":[41],"at":[42],"different":[43],"tempi.":[44],"This":[45],"can":[47],"be":[48],"achieved":[49],"by":[50,129],"expressing":[51],"time-axis":[53],"in":[54,100],"log-scale,":[55],"example":[57],"using":[58],"Scale":[60,82,122],"Transform":[61],"(ST).":[62],"Since":[63],"frequency":[65,102,142],"locations":[66],"content":[70,98],"are":[71],"also":[72],"important,":[73],"previously":[75],"extended":[76],"ST":[78],"Modulation":[81],"Spectrum":[83],"(MSS).":[84],"However,":[85],"MSS":[87],"does":[88],"not":[89],"represent":[92,136],"inter-relationship":[94],"between":[95,139],"existing":[99],"various":[101,141],"bands.":[103,143],"To":[104],"solve":[105],"issue,":[107],"here":[110],"representations.":[113],"The":[114],"first":[115],"one":[116],"based":[118],"on":[119,126],"2D":[121],"Transform,":[123],"second":[125],"statistics":[127,166],"(inspired":[128],"auditory":[131,165],"experiments":[132],"McDermott)":[134],"that":[135,161],"interrelationship":[138],"We":[144,159],"apply":[145],"both":[146],"task":[150],"class":[153],"recognition":[154,173],"demonstrates":[156],"their":[157],"benefits.":[158],"show":[160],"introduction":[163],"allows":[167],"large":[169],"increase":[170],"results.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}