{"id":"https://openalex.org/W3016050488","doi":"https://doi.org/10.1109/icassp40776.2020.9054578","title":"Stable Training of Dnn for Speech Enhancement Based on Perceptually-Motivated Black-Box Cost Function","display_name":"Stable Training of Dnn for Speech Enhancement Based on Perceptually-Motivated Black-Box Cost Function","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016050488","doi":"https://doi.org/10.1109/icassp40776.2020.9054578","mag":"3016050488"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5028960483","display_name":"Masaki Kawanaka","orcid":"https://orcid.org/0009-0008-0977-5642"},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masaki Kawanaka","raw_affiliation_strings":["National Institute of Technology, Tokuyama College, Yamaguchi, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College, Yamaguchi, Japan","institution_ids":["https://openalex.org/I4210142609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075732053","display_name":"Ryoichi Miyazaki","orcid":"https://orcid.org/0000-0002-5023-5380"},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Miyazaki","raw_affiliation_strings":["National Institute of Technology, Tokuyama College, Yamaguchi, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College, Yamaguchi, Japan","institution_ids":["https://openalex.org/I4210142609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Department of Intermedia Art and Science, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intermedia Art and Science, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028960483"],"corresponding_institution_ids":["https://openalex.org/I4210142609"],"apc_list":null,"apc_paid":null,"fwci":3.6368,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93726136,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7524","last_page":"7528"},"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":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.9836224317550659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720067501068115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6340457797050476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.604128897190094},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5237193703651428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47323286533355713},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.44364139437675476},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4347954988479614},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4298032820224762},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3378119468688965},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1007067859172821},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06233108043670654}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9836224317550659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720067501068115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6340457797050476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.604128897190094},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5237193703651428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47323286533355713},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.44364139437675476},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4347954988479614},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4298032820224762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3378119468688965},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1007067859172821},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06233108043670654},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W2099471712","https://openalex.org/W2144404214","https://openalex.org/W2170336381","https://openalex.org/W2288645994","https://openalex.org/W2527819024","https://openalex.org/W2603567530","https://openalex.org/W2619516334","https://openalex.org/W2696558042","https://openalex.org/W2785678896","https://openalex.org/W2802304149","https://openalex.org/W2805233667","https://openalex.org/W2889373351","https://openalex.org/W2940177920","https://openalex.org/W2943895317","https://openalex.org/W2949558265","https://openalex.org/W2962866211","https://openalex.org/W2963208657","https://openalex.org/W2963341071","https://openalex.org/W2963702144","https://openalex.org/W2963836885","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2972443522","https://openalex.org/W3015219411","https://openalex.org/W3015360216","https://openalex.org/W3103619082","https://openalex.org/W4293867591","https://openalex.org/W4302765731","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6692846177","https://openalex.org/W6727474214","https://openalex.org/W6735429107","https://openalex.org/W6738491991","https://openalex.org/W6748582592","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W3209446892","https://openalex.org/W2345688450","https://openalex.org/W4386746628","https://openalex.org/W1980687383","https://openalex.org/W2105126898","https://openalex.org/W2792294082"],"abstract_inverted_index":{"Improving":[0],"subjective":[1,20,179],"sound":[2,28,172],"quality":[3,29,173],"of":[4,9,40,46,81,106,114,138],"enhanced":[5],"signals":[6],"is":[7,55,104],"one":[8],"the":[10,19,72,79,96,107,111,115,136,145,159],"most":[11,59],"important":[12],"missions":[13],"in":[14,58,170],"speech":[15,41],"enhancement.":[16],"For":[17],"evaluating":[18],"quality,":[21],"several":[22],"methods":[23,176],"related":[24],"to":[25,68,77,123,134,154],"perceptually-motivated":[26],"objective":[27],"assessment":[30],"(OSQA)":[31],"have":[32],"been":[33],"proposed":[34,76,146],"such":[35,47],"as":[36,140],"PESQ":[37,139,161],"(perceptual":[38],"evaluation":[39],"quality).":[42],"However,":[43],"direct":[44],"use":[45,124],"measures":[48],"for":[49,94],"training":[50,95,108],"deep":[51],"neural":[52],"network":[53],"(DNN)":[54],"not":[56],"allowed":[57],"cases":[60],"because":[61],"popular":[62],"OSQAs":[63],"are":[64],"non-differentiable":[65],"with":[66,101],"respect":[67],"DNN":[69,86,153],"parameters.":[70],"Therefore,":[71],"previous":[73],"study":[74],"has":[75],"approximate":[78],"score":[80,137,162],"OS-QAs":[82],"by":[83,110],"an":[84,141],"auxiliary":[85],"so":[87],"that":[88,144],"its":[89],"gradient":[90],"can":[91,149],"be":[92],"used":[93],"primary":[97],"DNN.":[98],"One":[99],"problem":[100],"this":[102,119],"approach":[103],"instability":[105],"caused":[109],"approximation":[112],"error":[113],"score.":[116],"To":[117],"overcome":[118],"problem,":[120],"we":[121],"propose":[122],"stabilization":[125],"techniques":[126],"borrowed":[127],"from":[128],"reinforcement":[129],"learning.":[130],"The":[131],"experiments,":[132],"aimed":[133],"increase":[135,155],"example,":[142],"show":[143],"method":[147],"(i)":[148],"stably":[150],"train":[151],"a":[152,164],"PESQ,":[156],"(ii)":[157],"achieved":[158],"state-of-the-art":[160],"on":[163,178],"public":[165],"dataset,":[166],"and":[167],"(iii)":[168],"resulted":[169],"better":[171],"than":[174],"conventional":[175],"based":[177],"evaluation.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}