{"id":"https://openalex.org/W3110277971","doi":"https://doi.org/10.1109/lsp.2020.3039765","title":"Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding","display_name":"Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3110277971","doi":"https://doi.org/10.1109/lsp.2020.3039765","mag":"3110277971"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.3039765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3039765","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.00054","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047870570","display_name":"Kai Zhen","orcid":"https://orcid.org/0000-0003-4133-8158"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhen","raw_affiliation_strings":["Department of Computer Science and Cognitive Science Program, Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Cognitive Science Program, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005473429","display_name":"Mi Suk Lee","orcid":"https://orcid.org/0000-0001-8951-5032"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mi Suk Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033055249","display_name":"Jongmo Sung","orcid":"https://orcid.org/0000-0002-3396-1137"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongmo Sung","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071537541","display_name":"Seungkwon Beack","orcid":"https://orcid.org/0000-0002-6254-2062"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkwon Beack","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3513-8328","affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5384,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.83666133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"2159","last_page":"2163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.8306121230125427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7775408029556274},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.6788159608840942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6240731477737427},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.6232434511184692},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5056076049804688},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4662797451019287},{"id":"https://openalex.org/keywords/auditory-masking","display_name":"Auditory masking","score":0.4448702335357666},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.343367338180542},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.22334444522857666},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1251993179321289},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11468157172203064}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8306121230125427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775408029556274},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.6788159608840942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6240731477737427},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.6232434511184692},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5056076049804688},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4662797451019287},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.4448702335357666},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.343367338180542},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.22334444522857666},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1251993179321289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11468157172203064},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2020.3039765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3039765","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2101.00054","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.00054","pdf_url":"https://arxiv.org/pdf/2101.00054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.00054","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.00054","pdf_url":"https://arxiv.org/pdf/2101.00054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2859225421","display_name":null,"funder_award_id":"2017\u20100\u201000072","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1523644733","https://openalex.org/W1552314771","https://openalex.org/W1553834069","https://openalex.org/W2058075673","https://openalex.org/W2067295501","https://openalex.org/W2128301448","https://openalex.org/W2138115654","https://openalex.org/W2155729921","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2519091744","https://openalex.org/W2558649592","https://openalex.org/W2606176153","https://openalex.org/W2620812332","https://openalex.org/W2732044853","https://openalex.org/W2752796333","https://openalex.org/W2786008273","https://openalex.org/W2892110446","https://openalex.org/W2897371647","https://openalex.org/W2935711438","https://openalex.org/W2936088203","https://openalex.org/W2949382160","https://openalex.org/W2950237361","https://openalex.org/W2951535099","https://openalex.org/W2962946126","https://openalex.org/W2963045393","https://openalex.org/W2963091184","https://openalex.org/W2963182577","https://openalex.org/W2963208781","https://openalex.org/W2963452667","https://openalex.org/W2963799213","https://openalex.org/W2964121744","https://openalex.org/W2964164354","https://openalex.org/W2972354707","https://openalex.org/W2997901485","https://openalex.org/W3015268401","https://openalex.org/W6631190155","https://openalex.org/W6631257896","https://openalex.org/W6633114069","https://openalex.org/W6736723571","https://openalex.org/W6741057705","https://openalex.org/W6748015549","https://openalex.org/W6751512325","https://openalex.org/W6755853340"],"related_works":["https://openalex.org/W2892072280","https://openalex.org/W2130095015","https://openalex.org/W3034731095","https://openalex.org/W2996518094","https://openalex.org/W2364915322","https://openalex.org/W1485474031","https://openalex.org/W2185350064","https://openalex.org/W2789044730","https://openalex.org/W4226256361","https://openalex.org/W2144833687"],"abstract_inverted_index":{"Conventional":[0],"audio":[1,24,28,72,149],"coding":[2,73,150],"technologies":[3],"commonly":[4],"leverage":[5],"human":[6],"perception":[7],"of":[8,21,34,70],"sound,":[9],"or":[10],"psychoacoustics,":[11],"to":[12,40,51,65,84,109],"reduce":[13],"the":[14,18,22,31,35,52,67,85,99,104,116,120,135,153],"bitrate":[15],"while":[16],"preserving":[17],"perceptual":[19],"quality":[20,43],"decoded":[23],"signals.":[25],"For":[26],"neural":[27,71,122,140],"codecs,":[29],"however,":[30],"objective":[32],"nature":[33],"loss":[36,68,96],"function":[37,97],"usually":[38],"leads":[39],"suboptimal":[41],"sound":[42],"as":[44,46,125],"well":[45],"high":[47],"run-time":[48],"complexity":[49],"due":[50],"large":[53,126],"model":[54,92,118],"size.":[55],"In":[56],"this":[57],"work,":[58],"we":[59],"present":[60],"a":[61,89,138],"psychoacoustic":[62],"calibration":[63],"scheme":[64],"re-define":[66],"functions":[69],"systems":[74],"so":[75],"that":[76,107,115],"it":[77],"can":[78],"decode":[79],"signals":[80],"more":[81,130],"perceptually":[82],"similar":[83],"reference,":[86],"yet":[87],"with":[88,142,152],"much":[90],"lower":[91],"complexity.":[93],"The":[94],"proposed":[95,117,136],"incorporates":[98],"global":[100],"masking":[101],"threshold,":[102],"allowing":[103],"reconstruction":[105],"error":[106],"corresponds":[108],"inaudible":[110],"artifacts.":[111],"Experimental":[112],"results":[113],"show":[114],"outperforms":[119],"baseline":[121],"codec":[123,159],"twice":[124],"and":[127],"consuming":[128],"23.4%":[129],"bits":[131],"per":[132],"second.":[133],"With":[134],"method,":[137],"lightweight":[139],"codec,":[141],"only":[143],"0.9":[144],"million":[145],"parameters,":[146],"performs":[147],"near-transparent":[148],"comparable":[151],"commercial":[154],"MPEG-1":[155],"Audio":[156],"Layer":[157],"III":[158],"at":[160],"112":[161],"kbps.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-12-07T00:00:00"}
