{"id":"https://openalex.org/W2408467190","doi":"https://doi.org/10.1109/icassp.2016.7471747","title":"Equalization matching of speech recordings in real-world environments","display_name":"Equalization matching of speech recordings in real-world environments","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408467190","doi":"https://doi.org/10.1109/icassp.2016.7471747","mag":"2408467190"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471747","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/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Francois G. Germain","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044614923","display_name":"Gautham J. Mysore","orcid":"https://orcid.org/0000-0003-0483-9252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham J. Mysore","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039613934","display_name":"Takako Fujioka","orcid":"https://orcid.org/0000-0003-2421-9106"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takako Fujioka","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102812631"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.66677736,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8640531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"609","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7856522798538208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.738264799118042},{"id":"https://openalex.org/keywords/equalization","display_name":"Equalization (audio)","score":0.6953350305557251},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6720183491706848},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6180596351623535},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6160197257995605},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.58979731798172},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.528499186038971},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5019278526306152},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.323975533246994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2532534599304199},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.1810474693775177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13602668046951294},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13273000717163086},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12760376930236816},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11345210671424866},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.06636184453964233},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06142744421958923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856522798538208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.738264799118042},{"id":"https://openalex.org/C75755367","wikidata":"https://www.wikidata.org/wiki/Q104531076","display_name":"Equalization (audio)","level":3,"score":0.6953350305557251},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6720183491706848},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6180596351623535},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6160197257995605},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.58979731798172},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.528499186038971},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5019278526306152},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.323975533246994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2532534599304199},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.1810474693775177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13602668046951294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13273000717163086},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12760376930236816},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11345210671424866},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.06636184453964233},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06142744421958923},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471747","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W188967299","https://openalex.org/W285277413","https://openalex.org/W1495679096","https://openalex.org/W1512562331","https://openalex.org/W1527848610","https://openalex.org/W1601919122","https://openalex.org/W1755563775","https://openalex.org/W2013419672","https://openalex.org/W2058502470","https://openalex.org/W2071460053","https://openalex.org/W2086381917","https://openalex.org/W2098290609","https://openalex.org/W2105921478","https://openalex.org/W2115144768","https://openalex.org/W2127851351","https://openalex.org/W2153894152","https://openalex.org/W2162514423","https://openalex.org/W2401387233","https://openalex.org/W2565129795","https://openalex.org/W2797532987","https://openalex.org/W4233392025","https://openalex.org/W4245919820","https://openalex.org/W4296927107","https://openalex.org/W6630574771","https://openalex.org/W6731328355"],"related_works":["https://openalex.org/W2135485548","https://openalex.org/W2373767407","https://openalex.org/W2187949121","https://openalex.org/W2376606440","https://openalex.org/W2251439150","https://openalex.org/W4221152531","https://openalex.org/W2568425241","https://openalex.org/W1127445803","https://openalex.org/W3030102128","https://openalex.org/W4375869276"],"abstract_inverted_index":{"When":[0],"different":[1,17],"parts":[2],"of":[3,64,102],"speech":[4,46,66,108,115,173],"content":[5,63],"such":[6,45],"as":[7],"voice-overs":[8],"and":[9,20,35,67,94,116,126,179],"narration":[10],"are":[11,155,176],"recorded":[12,55],"in":[13,25,56,78,82,111,165,180],"real-world":[14],"environments":[15],"with":[16,147],"acoustic":[18],"properties":[19],"background":[21,68,117,163],"noise,":[22,118],"the":[23,29,57,61,65,83,98,128,133,143,151,162,166],"difference":[24],"sound":[26,51],"quality":[27],"between":[28],"recordings":[30,47],"is":[31,138],"typically":[32,70],"quite":[33],"audible":[34],"therefore":[36],"undesirable.":[37],"We":[38,105],"propose":[39,106],"an":[40],"algorithm":[41],"to":[42,113,123,140],"equalize":[43],"multiple":[44],"so":[48],"that":[49,188],"they":[50,53],"like":[52],"were":[54],"same":[58],"environment.":[59],"As":[60],"timbral":[62],"noise":[69,164],"differ":[71],"considerably,":[72],"a":[73,79],"simple":[74,193],"equalization":[75,88,121,194],"matching":[76,100,144],"results":[77],"noticeable":[80],"mismatch":[81],"output":[84,168],"signals.":[85],"A":[86],"single":[87],"filter":[89],"affects":[90],"both":[91],"timbres":[92],"equally":[93],"thus":[95],"cannot":[96],"disambiguate":[97,142],"competing":[99],"equations":[101,145],"each":[103,124,148],"source.":[104,149],"leveraging":[107],"enhancement":[109,174],"methods":[110,175],"order":[112],"separate":[114],"independently":[119,131],"apply":[120],"filtering":[122],"source,":[125],"recombine":[127],"outputs.":[129],"By":[130],"equalizing":[132],"separated":[134],"sources,":[135],"our":[136,189],"method":[137],"able":[139],"better":[141],"associated":[146],"Therefore":[150],"resulting":[152],"matched":[153],"signals":[154],"perceptually":[156,182],"very":[157],"similar.":[158],"Additionally,":[159],"by":[160],"retaining":[161],"final":[167],"signals,":[169],"most":[170],"artifacts":[171],"from":[172],"considerably":[177],"reduced":[178],"general":[181],"masked.":[183],"Subjective":[184],"listening":[185],"tests":[186],"show":[187],"approach":[190],"significantly":[191],"outperforms":[192],"matching.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}