{"id":"https://openalex.org/W4372266968","doi":"https://doi.org/10.1109/icassp49357.2023.10095046","title":"Metric-Oriented Speech Enhancement Using Diffusion Probabilistic Model","display_name":"Metric-Oriented Speech Enhancement Using Diffusion Probabilistic Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266968","doi":"https://doi.org/10.1109/icassp49357.2023.10095046"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074544822","display_name":"Yu\u2010Chen Hu","orcid":"https://orcid.org/0000-0002-5055-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040052184","display_name":"Weiwei Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weiwei Weng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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/metric","display_name":"Metric (unit)","score":0.8477160334587097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629008293151855},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6506614685058594},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5864347219467163},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5325435996055603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202373266220093},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5049896836280823},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.486829936504364},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4785909652709961},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.47360682487487793},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4105977416038513},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.225297749042511},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12362369894981384},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.10671225190162659}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.8477160334587097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629008293151855},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6506614685058594},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5864347219467163},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5325435996055603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202373266220093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5049896836280823},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.486829936504364},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4785909652709961},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.47360682487487793},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4105977416038513},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.225297749042511},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12362369894981384},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.10671225190162659},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2046376809","https://openalex.org/W2603567530","https://openalex.org/W2755891984","https://openalex.org/W2888442053","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963084599","https://openalex.org/W2963144852","https://openalex.org/W2963747784","https://openalex.org/W2995986219","https://openalex.org/W2998832642","https://openalex.org/W3015219411","https://openalex.org/W3016056257","https://openalex.org/W3036167779","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3109018774","https://openalex.org/W3129651364","https://openalex.org/W3160324929","https://openalex.org/W3168053944","https://openalex.org/W3180196270","https://openalex.org/W3183454191","https://openalex.org/W3184410885","https://openalex.org/W3206531472","https://openalex.org/W4221144097","https://openalex.org/W4221156109","https://openalex.org/W4297841258","https://openalex.org/W4312095920","https://openalex.org/W4375869103","https://openalex.org/W4375869127","https://openalex.org/W4375869189","https://openalex.org/W4385822727","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6788990321","https://openalex.org/W6798721538","https://openalex.org/W6809431739","https://openalex.org/W6846774901"],"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":{"Deep":[0],"neural":[1],"network":[2],"based":[3,88],"speech":[4,59],"enhancement":[5,60],"technique":[6],"focuses":[7],"on":[8],"learning":[9],"a":[10,57,75,96],"noisy-to-clean":[11],"transformation":[12],"supervised":[13],"by":[14],"paired":[15],"training":[16,36,42,77,118],"data.":[17],"However,":[18],"the":[19,35,41,65,69,92,101,105,121],"task-specific":[20],"evaluation":[21,45,93,128],"metric":[22,46,94],"(e.g.,":[23],"PESQ)":[24],"is":[25],"usually":[26],"non-differentiable":[27],"and":[28,44,73,119],"can":[29],"not":[30],"be":[31],"directly":[32],"constructed":[33],"in":[34,49,68,124],"criteria.":[37],"This":[38],"mismatch":[39],"between":[40],"objective":[43],"likely":[47],"results":[48,110],"sub-optimal":[50],"performance.":[51],"To":[52],"alleviate":[53],"it,":[54],"we":[55,84],"propose":[56],"metric-oriented":[58,76,117],"method":[61],"(MOSE),":[62],"which":[63],"leverages":[64],"recent":[66],"advances":[67],"diffusion":[70],"probabilistic":[71],"model":[72],"integrates":[74],"strategy":[78],"into":[79],"its":[80],"reverse":[81,102],"process.":[82],"Specifically,":[83],"design":[85],"an":[86],"actor-critic":[87],"framework":[89],"that":[90,112],"considers":[91],"as":[95],"posterior":[97],"reward,":[98],"thus":[99],"guiding":[100],"process":[103],"to":[104],"metric-increasing":[106],"direction.":[107],"The":[108],"experimental":[109],"demonstrate":[111],"MOSE":[113],"obviously":[114],"benefits":[115],"from":[116],"surpasses":[120],"generative":[122],"baselines":[123],"terms":[125],"of":[126],"all":[127],"metrics.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}