{"id":"https://openalex.org/W2774836813","doi":"https://doi.org/10.1109/taslp.2017.2779405","title":"A Pitch-Synchronous Simultaneous Detection-Estimation Framework for Speech Enhancement","display_name":"A Pitch-Synchronous Simultaneous Detection-Estimation Framework for Speech Enhancement","publication_year":2017,"publication_date":"2017-12-04","ids":{"openalex":"https://openalex.org/W2774836813","doi":"https://doi.org/10.1109/taslp.2017.2779405","mag":"2774836813"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2779405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2779405","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5063573595","display_name":"Johannes Stahl","orcid":"https://orcid.org/0000-0003-0833-1448"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Johannes Stahl","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0833-1448","affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088787456","display_name":"Pejman Mowlaee","orcid":"https://orcid.org/0000-0003-0136-8002"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Pejman Mowlaee","raw_affiliation_strings":["Signal Processing and Speech Communication Lab, Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0136-8002","affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Lab, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":1.3531,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82137082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"26","issue":"2","first_page":"436","last_page":"450"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9984999895095825,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6479668021202087},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6388997435569763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5513616800308228},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5401531457901001},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49679163098335266},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4742495119571686},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4466978907585144},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.315803587436676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2965514063835144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2591719925403595},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14064058661460876},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.14053860306739807},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13419857621192932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6479668021202087},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6388997435569763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5513616800308228},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5401531457901001},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49679163098335266},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4742495119571686},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4466978907585144},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.315803587436676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2965514063835144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2591719925403595},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14064058661460876},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.14053860306739807},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13419857621192932},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2779405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2779405","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W123426918","https://openalex.org/W639989723","https://openalex.org/W1495679096","https://openalex.org/W1536252645","https://openalex.org/W1552314771","https://openalex.org/W1861683848","https://openalex.org/W1968939597","https://openalex.org/W1973119332","https://openalex.org/W1975301756","https://openalex.org/W1990449877","https://openalex.org/W1993393237","https://openalex.org/W2015087354","https://openalex.org/W2051428568","https://openalex.org/W2058693698","https://openalex.org/W2072760465","https://openalex.org/W2098267193","https://openalex.org/W2109215269","https://openalex.org/W2111460811","https://openalex.org/W2118972378","https://openalex.org/W2121973264","https://openalex.org/W2128308310","https://openalex.org/W2135284480","https://openalex.org/W2141998673","https://openalex.org/W2144579212","https://openalex.org/W2152819669","https://openalex.org/W2153384885","https://openalex.org/W2155889651","https://openalex.org/W2156317483","https://openalex.org/W2158554386","https://openalex.org/W2310096243","https://openalex.org/W2398345641","https://openalex.org/W2478884216","https://openalex.org/W2539406037","https://openalex.org/W2613012181","https://openalex.org/W2619993508","https://openalex.org/W2620805210","https://openalex.org/W2752172708","https://openalex.org/W2774836813","https://openalex.org/W3008609509","https://openalex.org/W3147539069","https://openalex.org/W4211251910","https://openalex.org/W4253928870","https://openalex.org/W6639283174","https://openalex.org/W6682883272","https://openalex.org/W6712696842","https://openalex.org/W6737733355","https://openalex.org/W6738723988","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W4225639054","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W3043214604","https://openalex.org/W1967434260","https://openalex.org/W2402466562","https://openalex.org/W1505346162"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"methods":[2,185],"formulated":[3],"in":[4,12,21,27,117,186],"the":[5,13,18,22,28,31,49,73,104,107,114,133,149,156],"short-time":[6],"Fourier":[7],"transform":[8],"(STFT)":[9],"domain":[10],"vary":[11],"statistical":[14],"assumptions":[15],"made":[16],"on":[17,37],"STFT":[19],"coefficients,":[20],"optimization":[23],"criteria":[24],"applied":[25],"or":[26],"models":[29,65,135],"of":[30,48,106,136,159,188],"signal":[32,50,66,94],"components.":[33,75],"Recently,":[34],"approaches":[35],"relying":[36],"a":[38,84,92,165,173],"stochastic-deterministic":[39,180],"speech":[40,119,142,189],"model":[41,109,113],"have":[42],"been":[43],"proposed.":[44],"The":[45,62,177],"deterministic":[46,74],"part":[47,64],"corresponds":[51],"to":[52,58,100],"harmonically":[53],"related":[54],"sinusoids,":[55],"often":[56],"used":[57],"represent":[59],"voiced":[60,118,137],"speech.":[61],"stochastic":[63],"components":[67],"that":[68,169],"are":[69,144],"not":[70],"captured":[71],"by":[72,163,195],"In":[76],"this":[77,81],"paper,":[78],"we":[79,112,152],"consider":[80],"scenario":[82],"under":[83],"new":[85],"perspective":[86],"yielding":[87],"three":[88],"main":[89],"contributions.":[90],"First,":[91],"pitch-synchronous":[93,179],"representation":[95],"is":[96,170],"considered":[97],"and":[98,141,161,191,202],"shown":[99],"be":[101],"advantageous":[102],"for":[103,132,198],"estimation":[105,162],"harmonic":[108,115],"parameters.":[110],"Second,":[111],"amplitudes":[116],"as":[120],"random":[121],"variables":[122],"with":[123],"frequency":[124],"bin":[125],"dependent":[126],"Gamma":[127],"distributions.":[128],"Finally,":[129],"distinct":[130],"estimators":[131],"different":[134,203],"speech,":[138,140],"unvoiced":[139],"absence":[143],"derived.":[145],"To":[146],"select":[147],"from":[148,172],"arising":[150],"estimates,":[151],"take":[153],"into":[154],"account":[155],"mutual":[157],"impact":[158],"detection":[160],"proposing":[164],"binary":[166],"decision":[167],"framework":[168],"derived":[171],"Bayesian":[174],"risk":[175],"function.":[176],"resulting":[178],"estimator":[181],"outperforms":[182],"several":[183],"benchmark":[184],"terms":[187],"intelligibility":[190],"perceived":[192],"quality":[193],"predicted":[194],"instrumental":[196],"measures":[197],"various":[199],"noise":[200],"types":[201],"signal-to-noise":[204],"ratios.":[205]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}