{"id":"https://openalex.org/W3016163030","doi":"https://doi.org/10.1109/icassp40776.2020.9054334","title":"Pan: Phoneme-Aware Network for Monaural Speech Enhancement","display_name":"Pan: Phoneme-Aware Network for Monaural Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016163030","doi":"https://doi.org/10.1109/icassp40776.2020.9054334","mag":"3016163030"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054334","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/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058896884","display_name":"Ming Lei","orcid":"https://orcid.org/0000-0002-5712-3285"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Lei","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055433405","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-9053-9314"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001133136"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6522054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6634","last_page":"6638"},"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":0.9997000098228455,"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":0.9976999759674072,"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/monaural","display_name":"Monaural","score":0.9224148988723755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978155612945557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7812439203262329},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7603201866149902},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7195764780044556},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.687560498714447},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5029801726341248},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4227522611618042},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4158203601837158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33378076553344727},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16316384077072144}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9224148988723755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978155612945557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7812439203262329},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7603201866149902},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7195764780044556},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.687560498714447},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5029801726341248},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4227522611618042},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4158203601837158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33378076553344727},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16316384077072144},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054334","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/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1583048384","https://openalex.org/W1836465849","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W1989364685","https://openalex.org/W2017608047","https://openalex.org/W2069681747","https://openalex.org/W2141998673","https://openalex.org/W2171019095","https://openalex.org/W2219249508","https://openalex.org/W2398264106","https://openalex.org/W2517251061","https://openalex.org/W2518172956","https://openalex.org/W2889286744","https://openalex.org/W2889442120","https://openalex.org/W2899771611","https://openalex.org/W2940275453","https://openalex.org/W2962866211","https://openalex.org/W2963285578","https://openalex.org/W2963840672","https://openalex.org/W2972686346","https://openalex.org/W2981022124","https://openalex.org/W6638667902","https://openalex.org/W6668037159","https://openalex.org/W6685562342","https://openalex.org/W6688816777","https://openalex.org/W6696085341","https://openalex.org/W6756040250","https://openalex.org/W6837784546"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W3043214604","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2738829087"],"abstract_inverted_index":{"Current":[0],"methods":[1],"for":[2,54,83],"monaural":[3],"speech":[4,55,62,102,126],"enhancement":[5,63,90],"only":[6],"utilize":[7,50],"acoustic":[8],"information":[9,15,33,98],"but":[10],"seldom":[11],"consider":[12],"the":[13,20,31,35,41,51,58,74,89,96,111,118,123],"phonetic":[14,32,36,97],"of":[16,101,113],"an":[17,77],"utterance.":[18],"In":[19],"voice":[21],"conversion":[22],"community,":[23],"significant":[24],"progress":[25],"has":[26],"been":[27],"achieved":[28],"by":[29,40,94],"using":[30,95],"via":[34],"posteriorgrams":[37],"(PPGs).":[38],"Inspired":[39],"progress,":[42],"we":[43],"propose":[44],"a":[45,68],"phoneme-aware":[46],"network":[47],"(PAN)":[48],"to":[49,121],"noisy":[52],"PPGs":[53],"enhancement.":[56,127],"Since":[57],"PPG":[59,69,124],"prediction":[60],"and":[61,76,106],"benefit":[64],"from":[65],"each":[66],"other,":[67],"predictor":[70],"is":[71,81,92,117],"involved":[72],"into":[73,125],"PAN":[75],"iterative":[78],"training":[79],"algorithm":[80],"proposed":[82],"PAN.":[84],"Experimental":[85],"results":[86],"show":[87],"that":[88],"performance":[91],"improved":[93],"in":[99],"terms":[100],"intelligibility,":[103],"perceptual":[104],"quality":[105],"character":[107],"error":[108],"rate.":[109],"To":[110],"best":[112],"our":[114],"knowledge,":[115],"this":[116],"first":[119],"time":[120],"introduce":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}