{"id":"https://openalex.org/W3197284240","doi":"https://doi.org/10.21437/interspeech.2021-582","title":"Improving Perceptual Quality by Phone-Fortified Perceptual Loss Using Wasserstein Distance for Speech Enhancement","display_name":"Improving Perceptual Quality by Phone-Fortified Perceptual Loss Using Wasserstein Distance for Speech Enhancement","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197284240","doi":"https://doi.org/10.21437/interspeech.2021-582","mag":"3197284240"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5060785253","display_name":"Tsun-An Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsun-An Hsieh","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798840","display_name":"Cheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4272,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.98978465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9973000288009644,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9902999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7229508757591248},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6886430978775024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492868065834045},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5282691717147827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5141737461090088},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.499889612197876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23083439469337463},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11326166987419128},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06691166758537292},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06568002700805664}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7229508757591248},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6886430978775024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492868065834045},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5282691717147827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5141737461090088},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.499889612197876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23083439469337463},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11326166987419128},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06691166758537292},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06568002700805664},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1920741591","https://openalex.org/W2044893557","https://openalex.org/W2070316439","https://openalex.org/W2094461119","https://openalex.org/W2094721231","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2331128040","https://openalex.org/W2405774341","https://openalex.org/W2502312327","https://openalex.org/W2603777577","https://openalex.org/W2799900537","https://openalex.org/W2802304149","https://openalex.org/W2883583470","https://openalex.org/W2889442120","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2892356933","https://openalex.org/W2912191105","https://openalex.org/W2937484199","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2949756029","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2963351212","https://openalex.org/W2963403924","https://openalex.org/W2972443522","https://openalex.org/W2972481755","https://openalex.org/W2973049979","https://openalex.org/W2987989623","https://openalex.org/W2991015288","https://openalex.org/W3016129867","https://openalex.org/W3096159803","https://openalex.org/W3096408984","https://openalex.org/W3163827866","https://openalex.org/W3209141406","https://openalex.org/W4297808394","https://openalex.org/W4301350573"],"related_works":["https://openalex.org/W1600259599","https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2904225411","https://openalex.org/W1630865680","https://openalex.org/W2169921015","https://openalex.org/W2061937230","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"aims":[3],"to":[4,14,112,129],"improve":[5],"speech":[6,19],"quality":[7,138],"and":[8,27,139],"intelligibility,":[9],"which":[10],"are":[11],"both":[12],"related":[13],"a":[15,33,66,123],"smooth":[16],"transition":[17],"in":[18,134],"segments":[20],"that":[21,39,70,99,118],"may":[22],"carry":[23],"linguistic":[24],"information,":[25,53],"e.g.phones":[26],"syllables.In":[28],"this":[29],"study,":[30],"we":[31],"propose":[32],"novel":[34],"phonefortified":[35],"perceptual":[36,107],"loss":[37],"(PFPL)":[38],"takes":[40],"phonetic":[41,52,73],"information":[42],"into":[43],"account":[44],"for":[45],"training":[46],"SE":[47,127],"models.To":[48],"effectively":[49],"incorporate":[50],"the":[51,54,63,78,82,85,88,92,100,106,115,119,143],"PFPL":[55,86,101,120],"is":[56,102],"computed":[57],"based":[58],"on":[59,142],"latent":[60,83],"representations":[61],"of":[62,81,136],"wav2vec":[64],"model,":[65],"powerful":[67],"selfsupervised":[68],"encoder":[69],"renders":[71],"rich":[72],"information.To":[74],"more":[75,103],"accurately":[76],"measure":[77],"distribution":[79],"distances":[80],"representations,":[84],"adopts":[87],"Wasserstein":[89],"distance":[90,93],"as":[91,110],"measure.Our":[94],"experimental":[95],"results":[96,116],"first":[97],"reveal":[98],"correlated":[104],"with":[105],"evaluation":[108],"metrics,":[109],"compared":[111],"signal-level":[113],"losses.Moreover,":[114],"showed":[117],"can":[121],"enable":[122],"deep":[124],"complex":[125],"U-Net":[126],"model":[128],"achieve":[130],"highly":[131],"competitive":[132],"performance":[133],"terms":[135],"standardized":[137],"intelligibility":[140],"evaluations":[141],"Voice":[144],"Bank-DEMAND":[145],"dataset.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
