{"id":"https://openalex.org/W2746601360","doi":"https://doi.org/10.21437/interspeech.2017-1504","title":"A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation","display_name":"A Comparison of Perceptually Motivated Loss Functions for Binary Mask Estimation in Speech Separation","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746601360","doi":"https://doi.org/10.21437/interspeech.2017-1504","mag":"2746601360"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1504","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5067398774","display_name":"Danny Websdale","orcid":"https://orcid.org/0000-0002-6856-772X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danny Websdale","raw_affiliation_strings":["School of Computing Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["School of Computing Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9338,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75890542,"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":"2003","last_page":"2007"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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/binary-number","display_name":"Binary number","score":0.6957013607025146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6462127566337585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6163785457611084},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5062033534049988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4268144965171814},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4125578999519348},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34482449293136597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2131107747554779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08974739909172058},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08342882990837097},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.06701147556304932}],"concepts":[{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6957013607025146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462127566337585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6163785457611084},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5062033534049988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268144965171814},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4125578999519348},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34482449293136597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2131107747554779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08974739909172058},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08342882990837097},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.06701147556304932},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-1504","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:64073","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G455538984","display_name":null,"funder_award_id":"EP/M014053/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W36796721","https://openalex.org/W75153181","https://openalex.org/W289804034","https://openalex.org/W596662218","https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1502364872","https://openalex.org/W1543299179","https://openalex.org/W1643320849","https://openalex.org/W1893876709","https://openalex.org/W1963970749","https://openalex.org/W1964538581","https://openalex.org/W1979099822","https://openalex.org/W1994396704","https://openalex.org/W2015143272","https://openalex.org/W2017608047","https://openalex.org/W2027701650","https://openalex.org/W2030680983","https://openalex.org/W2041638389","https://openalex.org/W2046869671","https://openalex.org/W2055516313","https://openalex.org/W2057200980","https://openalex.org/W2057889776","https://openalex.org/W2085191029","https://openalex.org/W2116251645","https://openalex.org/W2137075158","https://openalex.org/W2138456300","https://openalex.org/W2168379380","https://openalex.org/W2227273290","https://openalex.org/W2315268655","https://openalex.org/W2316870419","https://openalex.org/W2318802957","https://openalex.org/W2516001803","https://openalex.org/W2561557072"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W4385464961","https://openalex.org/W4308092240","https://openalex.org/W2060903012","https://openalex.org/W2021161555","https://openalex.org/W4400836012"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"and":[3,109,117,137,141],"compares":[4],"perceptually":[5,124,152],"motivated":[6,125,153],"loss":[7,20,35,60,69,84,101,126,154],"functions":[8,21,36,127,155],"for":[9,16],"deep":[10],"learning":[11],"based":[12],"binary":[13,73],"mask":[14,29,74],"estimation":[15,30],"speech":[17,56],"separation.":[18],"Previous":[19],"have":[22],"focused":[23],"on":[24],"maximising":[25],"classification":[26,78,94,115],"accuracy":[27,116],"of":[28,93,122,150],"but":[31],"we":[32],"now":[33],"propose":[34,81,98],"that":[37,86,103],"aim":[38],"to":[39,51,55,134,156],"maximise":[40],"the":[41,88,123,129,151],"hit":[42],"mi-":[43],"nus":[44],"false-alarm":[45],"(HIT-FA)":[46],"rate":[47,90,136],"which":[48,76],"is":[49,62,104],"known":[50],"correlate":[52],"more":[53],"closely":[54],"intelligibility.":[57],"The":[58],"baseline":[59],"function":[61,70,85,102],"bi-":[63],"nary":[64],"cross-entropy":[65],"(CE),":[66],"a":[67,83,99,105,112,157],"standard":[68],"used":[71],"in":[72],"estimation,":[75],"maximises":[77,87],"accuracy.":[79,95],"We":[80,96],"first":[82],"HIT-FA":[89,118,135],"in-":[91],"stead":[92],"then":[97,146],"second":[100],"hybrid":[106],"between":[107,114],"CE":[108],"HIT-FA,":[110],"providing":[111],"balance":[113],"rate.":[119],"Eval-":[120],"uations":[121],"with":[128],"GRID":[130],"database":[131],"show":[132],"improvements":[133],"ESTOI":[138],"across":[139],"babble":[140],"factory":[142],"noises.":[143],"Further":[144],"tests":[145],"explore":[147],"ap-":[148],"plication":[149],"larger":[158],"vocabulary":[159],"dataset.":[160]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}