{"id":"https://openalex.org/W7148388341","doi":"https://doi.org/10.1109/asru65441.2025.11433847","title":"Pitch-Assistant Harmonic Recovery for Efficient Speech Enhancement","display_name":"Pitch-Assistant Harmonic Recovery for Efficient Speech Enhancement","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148388341","doi":"https://doi.org/10.1109/asru65441.2025.11433847"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11433847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132805388","display_name":"Biao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Biao Liu","raw_affiliation_strings":["Institute of Acoustics Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085101543","display_name":"Zengqiang Shang","orcid":"https://orcid.org/0000-0002-9225-2138"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengqiang Shang","raw_affiliation_strings":["Institute of Acoustics Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyuan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyuan Xie","raw_affiliation_strings":["Jilin University,Changchun,China"],"affiliations":[{"raw_affiliation_string":"Jilin University,Changchun,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121048306","display_name":"Mou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125301","display_name":"Health Awareness (United States)","ror":"https://ror.org/03cc5yw72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125301"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mou Wang","raw_affiliation_strings":["Hardware Engineering System OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Hardware Engineering System OPPO,Beijing,China","institution_ids":["https://openalex.org/I4210125301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121038020","display_name":"Xin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125301","display_name":"Health Awareness (United States)","ror":"https://ror.org/03cc5yw72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125301"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Hardware Engineering System OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Hardware Engineering System OPPO,Beijing,China","institution_ids":["https://openalex.org/I4210125301"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132811048","display_name":"Pengyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Institute of Acoustics Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132805388"],"corresponding_institution_ids":["https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74154256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9879000186920166,"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":0.9879000186920166,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.005499999970197678,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.00139999995008111,"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/speech-enhancement","display_name":"Speech enhancement","score":0.6908000111579895},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4221999943256378},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3499000072479248},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.32989999651908875},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32269999384880066},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.32019999623298645}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6908000111579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5121999979019165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4713999927043915},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11433847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2889442120","https://openalex.org/W2963091184","https://openalex.org/W3015424358","https://openalex.org/W3015526955","https://openalex.org/W3028019732","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3134066280","https://openalex.org/W3160085755","https://openalex.org/W3161480375","https://openalex.org/W3162493033","https://openalex.org/W3165227983","https://openalex.org/W3197260772","https://openalex.org/W3197627016","https://openalex.org/W4213154531","https://openalex.org/W4225302959","https://openalex.org/W4375868823","https://openalex.org/W4384080510","https://openalex.org/W4385756463","https://openalex.org/W4392903568","https://openalex.org/W4401452051","https://openalex.org/W4408353997","https://openalex.org/W4412722447"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,44,98,107,111],"rapid":[2],"development":[3],"of":[4,47,100],"low-resource":[5],"online":[6,37,148],"speech":[7,31,38,48,128],"enhancement":[8,39],"models,":[9],"noise":[10,51,88],"suppression":[11],"can":[12],"now":[13],"be":[14],"achieved":[15],"with":[16,139],"significantly":[17,140],"fewer":[18],"model":[19,67,79,108],"parameters.":[20],"However,":[21],"these":[22],"models":[23],"often":[24],"suffer":[25],"from":[26],"limited":[27],"effectiveness":[28],"in":[29,57],"preserving":[30],"quality.":[32,59],"In":[33,60],"particular,":[34],"most":[35],"existing":[36,132],"methods":[40],"tend":[41],"to":[42,54,86,96,109,131],"distort":[43],"harmonic":[45,101,114],"structure":[46,115],"while":[49,90],"performing":[50],"reduction,":[52],"leading":[53],"noticeable":[55],"degradation":[56],"perceptual":[58,127],"this":[61],"paper,":[62],"we":[63],"propose":[64],"a":[65],"novel":[66],"architecture":[68],"called":[69],"Pitch-Assistant":[70],"Harmonic":[71],"Recovery":[72],"for":[73,147],"Efficient":[74],"Speech":[75],"Enhancement":[76],"(PHRSE).":[77],"The":[78],"operates":[80],"on":[81],"low-dimensional":[82],"Bark-scale":[83],"spectral":[84],"features":[85],"perform":[87],"suppression,":[89],"leveraging":[91],"estimated":[92],"fundamental":[93],"frequency":[94],"information":[95],"guide":[97],"reconstruction":[99],"components.":[102],"This":[103],"pitch-guided":[104],"strategy":[105],"enables":[106],"preserve":[110],"speech\u2019s":[112],"natural":[113],"more":[116],"effectively.":[117],"Experimental":[118],"results":[119],"demonstrate":[120],"that":[121],"PHRSE":[122],"not":[123],"only":[124],"achieves":[125],"higher":[126],"quality":[129],"compared":[130],"benchmarks,":[133],"but":[134],"also":[135],"maintains":[136],"real-time":[137],"performance":[138],"lower":[141],"computational":[142],"overhead,":[143],"making":[144],"it":[145],"suitable":[146],"and":[149],"resource-constrained":[150],"scenarios.":[151]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}