{"id":"https://openalex.org/W2805233667","doi":"https://doi.org/10.1109/taslp.2018.2842156","title":"DNN-Based Source Enhancement to Increase Objective Sound Quality Assessment Score","display_name":"DNN-Based Source Enhancement to Increase Objective Sound Quality Assessment Score","publication_year":2018,"publication_date":"2018-05-30","ids":{"openalex":"https://openalex.org/W2805233667","doi":"https://doi.org/10.1109/taslp.2018.2842156","mag":"2805233667"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2842156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2842156","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.09137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Nippon Telegraph and Telephone (NTT) Media Intelligence Laboratories, NTT Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3645-6213","affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone (NTT) Media Intelligence Laboratories, NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046170826","display_name":"Kenta Niwa","orcid":"https://orcid.org/0000-0002-6911-0238"},"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":"Kenta Niwa","raw_affiliation_strings":["Nippon Telegraph and Telephone (NTT) Media Intelligence Laboratories, NTT Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6911-0238","affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone (NTT) Media Intelligence Laboratories, NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069841141","display_name":"Yusuke Hioka","orcid":"https://orcid.org/0000-0003-3380-9677"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yusuke Hioka","raw_affiliation_strings":["Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0003-3380-9677","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046289","display_name":"Kazunori Kobayashi","orcid":null},"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":"Kazunori Kobayashi","raw_affiliation_strings":["Nippon Telegraph and Telephone (NTT) Media Intelligence Laboratories, NTT Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone (NTT) Media Intelligence Laboratories, NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002515983","display_name":"Yoichi Haneda","orcid":"https://orcid.org/0000-0001-8477-6575"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Haneda","raw_affiliation_strings":["Department of Informatics, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8477-6575","affiliations":[{"raw_affiliation_string":"Department of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":7.3537,"has_fulltext":true,"cited_by_count":73,"citation_normalized_percentile":{"value":0.97883053,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"26","issue":"10","first_page":"1780","last_page":"1792"},"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/pesq","display_name":"PESQ","score":0.6883293390274048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5958428382873535},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5387287139892578},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5369091033935547},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5301315188407898},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4902808964252472},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4453417658805847},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4368080794811249},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4220018684864044},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4134274423122406},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3503395915031433},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3409309983253479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.307466059923172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2770686149597168},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.2643744945526123}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6883293390274048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5958428382873535},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5387287139892578},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5369091033935547},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5301315188407898},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4902808964252472},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4453417658805847},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4368080794811249},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4220018684864044},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4134274423122406},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3503395915031433},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3409309983253479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.307466059923172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2770686149597168},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2643744945526123},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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":4,"locations":[{"id":"doi:10.1109/taslp.2018.2842156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2842156","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1810.09137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.09137","pdf_url":"https://arxiv.org/pdf/1810.09137","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"},{"id":"pmh:oai:irdb.nii.ac.jp:00931:0003059723","is_oa":true,"landing_page_url":"https://uec.repo.nii.ac.jp/records/8887","pdf_url":"https://uec.repo.nii.ac.jp/record/8887/files/JYH002.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/42550","is_oa":false,"landing_page_url":"http://hdl.handle.net/2292/42550","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.09137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.09137","pdf_url":"https://arxiv.org/pdf/1810.09137","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":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W1965255698","https://openalex.org/W1973669708","https://openalex.org/W1992022774","https://openalex.org/W2005981242","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2059005446","https://openalex.org/W2061678360","https://openalex.org/W2066460453","https://openalex.org/W2078528584","https://openalex.org/W2083686669","https://openalex.org/W2095595785","https://openalex.org/W2099655464","https://openalex.org/W2105029768","https://openalex.org/W2119717200","https://openalex.org/W2127851351","https://openalex.org/W2128402994","https://openalex.org/W2135823751","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2142027531","https://openalex.org/W2150543128","https://openalex.org/W2155027007","https://openalex.org/W2160306971","https://openalex.org/W2170336381","https://openalex.org/W2221409856","https://openalex.org/W2257979135","https://openalex.org/W2289394825","https://openalex.org/W2397226255","https://openalex.org/W2404892923","https://openalex.org/W2408744528","https://openalex.org/W2468525508","https://openalex.org/W2516547830","https://openalex.org/W2519994964","https://openalex.org/W2539201257","https://openalex.org/W2584991819","https://openalex.org/W2596331462","https://openalex.org/W2609317876","https://openalex.org/W2673599284","https://openalex.org/W2695081499","https://openalex.org/W2696558042","https://openalex.org/W2744073127","https://openalex.org/W2774425939","https://openalex.org/W2791874741","https://openalex.org/W2891607145","https://openalex.org/W2919115771","https://openalex.org/W2954695182","https://openalex.org/W2963341071","https://openalex.org/W3147539069","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4235765578","https://openalex.org/W6631190155","https://openalex.org/W6683204974","https://openalex.org/W6712317276","https://openalex.org/W6735168207","https://openalex.org/W6739877063","https://openalex.org/W6754901823"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,38,128,143,147,150,167],"training":[3,142],"method":[4,158],"for":[5,68,141,159],"deep":[6],"neural":[7],"network":[8],"(DNN)":[9],"based":[10],"source":[11],"enhancement":[12],"to":[13,41,47,73,85,181,210],"increase":[14,74,211],"objective":[15,52,108,124],"sound":[16],"quality":[17],"assessment":[18],"(OSQA)":[19],"scores":[20,63,76,94,197,232],"such":[21,54],"as":[22,37,55],"the":[23,56,82,104,107,119,122,133,155,161,164,175,183,188,201,206,212,216,237,242],"perceptual":[24],"evaluation":[25],"of":[26,106,121,135,166,187,214],"speech":[27],"quality.":[28],"In":[29],"many":[30],"conventional":[31],"studies,":[32],"DNNs":[33,72,178,207],"have":[34,64],"been":[35,65],"used":[36,66,140,180],"mapping":[39],"function":[40,53,109,186],"estimate":[42,182],"time-frequency":[43],"masks":[44],"and":[45,205],"trained":[46,209],"minimize":[48],"an":[49],"analytically":[50,97],"tractable":[51],"mean":[57],"squared":[58],"error":[59],"(MSE).":[60],"Since":[61],"OSQA":[62,75,93,193,196,223,231],"widely":[67],"sound-quality":[69],"evaluation,":[70],"constructing":[71],"would":[77],"be":[78,111],"better":[79],"than":[80],"using":[81,174],"minimum":[83],"MSE":[84,243],"create":[86],"high-quality":[87],"output":[88,172,189,203,218],"signals.":[89],"However,":[90],"since":[91],"most":[92],"are":[95,101,179,198,208],"not":[96,245],"tractable,":[98],"i.e.,":[99],"they":[100],"black":[102],"boxes,":[103],"gradient":[105,120,157,162],"cannot":[110],"calculated":[112,199],"by":[113,235],"simply":[114],"applying":[115,236],"backpropagation.":[116],"To":[117,170],"calculate":[118],"OSQA-based":[123],"function,":[125],"we":[126,153,228],"formulated":[127],"DNN":[129],"optimization":[130],"scheme":[131],"on":[132,163],"basis":[134,165],"black-box":[136],"optimization,":[137],"which":[138],"is":[139],"computer":[144],"that":[145,191,220,230],"plays":[146],"game.":[148],"For":[149],"black-box-optimization":[151],"scheme,":[152],"adopt":[154],"policy":[156],"calculating":[160],"sampling":[168,176],"algorithm.":[169],"simulate":[171],"signals":[173,190,219],"algorithm,":[177],"probability":[184,213],"density":[185],"maximize":[192],"scores.":[194,224],"The":[195],"from":[200],"simulated":[202,217],"signals,":[204],"generating":[215],"achieve":[221],"high":[222],"Through":[225],"several":[226],"experiments,":[227],"found":[229],"significantly":[233],"increased":[234],"proposed":[238],"method,":[239],"even":[240],"though":[241],"was":[244],"minimized.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":4}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}