{"id":"https://openalex.org/W3147913971","doi":"https://doi.org/10.1109/slt48900.2021.9383499","title":"Can We Trust Deep Speech Prior?","display_name":"Can We Trust Deep Speech Prior?","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3147913971","doi":"https://doi.org/10.1109/slt48900.2021.9383499","mag":"3147913971"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5005314366","display_name":"Ying Shi","orcid":"https://orcid.org/0000-0002-8693-7325"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Ying Shi","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905561","display_name":"Haolin Chen","orcid":"https://orcid.org/0000-0003-1791-6560"},"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolin Chen","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Zhiyuan Tang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Lantian Li","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391397","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-5501-6761"},"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":["Center for Speech and Language Technologies, Tsinghua University, China","Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005314366"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40344828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"742","last_page":"749"},"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":0.9983999729156494,"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":0.9975000023841858,"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/prior-probability","display_name":"Prior probability","score":0.7661436200141907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7533608675003052},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5845954418182373},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5605571269989014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591654777526855},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5485542416572571},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5454857349395752},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5148802995681763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5059227347373962},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4801841974258423},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45916494727134705},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.45727068185806274},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4406175911426544},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4102160334587097},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33706778287887573},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3040701448917389},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17289778590202332},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12199902534484863},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09479907155036926}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7661436200141907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533608675003052},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5845954418182373},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5605571269989014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591654777526855},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5485542416572571},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5454857349395752},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5148802995681763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5059227347373962},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4801841974258423},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45916494727134705},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.45727068185806274},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4406175911426544},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4102160334587097},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33706778287887573},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3040701448917389},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17289778590202332},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12199902534484863},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09479907155036926},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1583912456","https://openalex.org/W1631909651","https://openalex.org/W1902027874","https://openalex.org/W1959608418","https://openalex.org/W1975301756","https://openalex.org/W1995190897","https://openalex.org/W2016254085","https://openalex.org/W2036328773","https://openalex.org/W2039844283","https://openalex.org/W2075098731","https://openalex.org/W2099471712","https://openalex.org/W2124149378","https://openalex.org/W2128653836","https://openalex.org/W2137443926","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2147299274","https://openalex.org/W2157614506","https://openalex.org/W2165630397","https://openalex.org/W2187089797","https://openalex.org/W2409550820","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2620676623","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2895363208","https://openalex.org/W2905196628","https://openalex.org/W2933957542","https://openalex.org/W2949382160","https://openalex.org/W2963047245","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2963546708","https://openalex.org/W2963636093","https://openalex.org/W2963816101","https://openalex.org/W2992035660","https://openalex.org/W3005621653","https://openalex.org/W3100968126","https://openalex.org/W3127686677","https://openalex.org/W3150807214","https://openalex.org/W4214498238","https://openalex.org/W4253928870","https://openalex.org/W4256217162","https://openalex.org/W4289761690","https://openalex.org/W4293849739","https://openalex.org/W4297798428","https://openalex.org/W4320013936","https://openalex.org/W6635084905","https://openalex.org/W6640963894","https://openalex.org/W6683090638","https://openalex.org/W6714644935","https://openalex.org/W6738494546","https://openalex.org/W6738536549","https://openalex.org/W6752910514","https://openalex.org/W6755522362","https://openalex.org/W6761604041","https://openalex.org/W6770847983","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840","https://openalex.org/W2146544734"],"abstract_inverted_index":{"Recently,":[0],"speech":[1,7,31,92,108],"enhancement":[2],"(SE)":[3],"based":[4,105],"on":[5,99,106],"deep":[6,46,69,83,107,140],"prior":[8],"has":[9],"attracted":[10],"much":[11,75],"attention,":[12],"such":[13,35],"as":[14,36],"the":[15,42,51,61,78,91,118,134,137,144,147],"variational":[16],"auto-encoder":[17],"with":[18,38,74,90],"non-negative":[19],"matrix":[20],"factorization":[21],"(VAE-NMF)":[22],"architecture.":[23],"Compared":[24],"to":[25,49],"conventional":[26],"approaches":[27],"that":[28,68,104,127],"represent":[29,50],"clean":[30,52],"by":[32,81],"shallow":[33],"models":[34,48,142],"Gaussians":[37],"a":[39,57,82,96,110],"low-rank":[40],"covariance,":[41],"new":[43],"approach":[44],"employs":[45],"generative":[47,84,141],"speech,":[53],"which":[54],"often":[55],"provides":[56],"better":[58],"prior.":[59],"Despite":[60],"clear":[62],"advantage":[63],"in":[64,133],"theory,":[65],"we":[66],"argue":[67],"priors":[70],"must":[71],"be":[72,115,121],"used":[73],"caution,":[76],"since":[77],"likelihood":[79],"produced":[80],"model":[85],"does":[86],"not":[87],"always":[88],"coincide":[89],"quality.":[93],"We":[94],"designed":[95],"comprehensive":[97],"study":[98],"this":[100,128],"issue":[101],"and":[102,143],"demonstrated":[103],"priors,":[109],"reasonable":[111],"SE":[112],"performance":[113],"can":[114],"achieved,":[116],"but":[117],"results":[119],"might":[120],"suboptimal.":[122],"A":[123],"careful":[124],"analysis":[125],"showed":[126],"problem":[129],"is":[130],"deeply":[131],"rooted":[132],"disharmony":[135],"between":[136],"flexibility":[138],"of":[139,146],"nature":[145],"maximum-likelihood":[148],"(ML)":[149],"training.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}