{"id":"https://openalex.org/W3160971452","doi":"https://doi.org/10.1109/icassp39728.2021.9414761","title":"Phoneme-Based Distribution Regularization for Speech Enhancement","display_name":"Phoneme-Based Distribution Regularization for Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160971452","doi":"https://doi.org/10.1109/icassp39728.2021.9414761","mag":"3160971452"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100629029","display_name":"Yajing Liu","orcid":"https://orcid.org/0000-0001-5467-5976"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajing Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024977056","display_name":"Xiulian Peng","orcid":"https://orcid.org/0000-0001-8213-4878"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulian Peng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008612863","display_name":"Zhiwei Xiong","orcid":"https://orcid.org/0000-0002-9787-7460"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xiong","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100756584","display_name":"Yan Lu","orcid":"https://orcid.org/0000-0001-5383-6424"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6177,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65803039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2017","issue":null,"first_page":"726","last_page":"730"},"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":0.9987999796867371,"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/T13289","display_name":"Infant Health and Development","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7780726552009583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7429786324501038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7104405760765076},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5883859395980835},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5019388198852539},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4956320524215698},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4619899392127991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44488412141799927},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4195627272129059},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3309408724308014},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23530668020248413}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7780726552009583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429786324501038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7104405760765076},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5883859395980835},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5019388198852539},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4956320524215698},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4619899392127991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44488412141799927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4195627272129059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3309408724308014},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23530668020248413},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icassp39728.2021.9414761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W2193413348","https://openalex.org/W2291877678","https://openalex.org/W2296167893","https://openalex.org/W2398264106","https://openalex.org/W2536160108","https://openalex.org/W2561557072","https://openalex.org/W2747874407","https://openalex.org/W2749799511","https://openalex.org/W2889442120","https://openalex.org/W2892356933","https://openalex.org/W2897371647","https://openalex.org/W2949756029","https://openalex.org/W2963189033","https://openalex.org/W2963609956","https://openalex.org/W2982223350","https://openalex.org/W3016185664","https://openalex.org/W6687566353","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W3211091508","https://openalex.org/W642007152","https://openalex.org/W2056066842"],"abstract_inverted_index":{"Existing":[0],"speech":[1,6,45,56,64,101,129,153,177],"enhancement":[2,65,102,130,154,178],"methods":[3],"mainly":[4],"separate":[5],"from":[7],"noises":[8],"at":[9],"the":[10,15,23,100,141,149,157,165],"signal":[11],"level":[12],"or":[13],"in":[14,67,80],"time-frequency":[16],"domain.":[17],"They":[18],"seldom":[19],"pay":[20],"attention":[21],"to":[22,35,43,76,84,98,120],"semantic":[24],"information":[25,62],"of":[26,160],"a":[27,50,68,86,94],"corrupted":[28],"signal.":[29],"In":[30,123],"this":[31,37,124],"paper,":[32],"we":[33,48,82,126],"aim":[34],"bridge":[36],"gap":[38],"by":[39,132],"extracting":[40],"phoneme":[41,61,95],"identities":[42],"help":[44],"enhancement.":[46],"Specifically,":[47],"propose":[49,83],"phoneme-based":[51],"distribution":[52],"regularization":[53],"(PbDr)":[54],"for":[55,152],"enhancement,":[57],"which":[58,116],"incorporates":[59],"frame-wise":[60,111],"into":[63,175],"network":[66],"conditional":[69],"manner.":[70],"As":[71],"different":[72,77],"phonemes":[73],"always":[74],"lead":[75],"feature":[78],"distributions":[79],"frequency,":[81],"learn":[85],"parameter":[87,106],"pair,":[88],"i.e.":[89],"scale":[90],"and":[91],"bias,":[92],"through":[93],"classification":[96],"vector":[97],"modulate":[99],"network.":[103],"The":[104],"modulation":[105],"pair":[107],"includes":[108],"not":[109,146],"only":[110,147],"but":[112,155],"also":[113,156],"frequency-wise":[114],"conditions,":[115],"effectively":[117],"map":[118],"features":[119,131],"phoneme-related":[121],"distributions.":[122],"way,":[125],"explicitly":[127],"regularize":[128],"recognition":[133,158],"vectors.":[134],"Experiments":[135],"on":[136,164],"public":[137],"datasets":[138],"demonstrate":[139],"that":[140],"proposed":[142],"PbDr":[143,169],"module":[144,170],"can":[145],"boost":[148],"perceptual":[150],"quality":[151],"accuracy":[159],"an":[161],"ASR":[162],"system":[163],"enhanced":[166],"speech.":[167],"This":[168],"could":[171],"be":[172],"readily":[173],"incorporated":[174],"other":[176],"networks":[179],"as":[180],"well.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}