{"id":"https://openalex.org/W3096900631","doi":"https://doi.org/10.21437/interspeech.2020-1047","title":"An NMF-HMM Speech Enhancement Method Based on Kullback-Leibler Divergence","display_name":"An NMF-HMM Speech Enhancement Method Based on Kullback-Leibler Divergence","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096900631","doi":"https://doi.org/10.21437/interspeech.2020-1047","mag":"3096900631"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1047","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/4f30e2af-47f8-4391-a33f-c3fdb40033b9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029253113","display_name":"Yang Xiang","orcid":"https://orcid.org/0000-0002-7120-5842"},"institutions":[{"id":"https://openalex.org/I4210133201","display_name":"Media Design School","ror":"https://ror.org/03cybp342","country_code":"NZ","type":"education","lineage":["https://openalex.org/I4210133201"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Department of Architecture, Design and Media Technology"],"affiliations":[{"raw_affiliation_string":"Department of Architecture, Design and Media Technology","institution_ids":["https://openalex.org/I4210133201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084126009","display_name":"Liming Shi","orcid":"https://orcid.org/0000-0003-4129-0668"},"institutions":[{"id":"https://openalex.org/I4210134959","display_name":"Faculty of Design","ror":"https://ror.org/04bw0hg47","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210134959"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Liming Shi","raw_affiliation_strings":["The Technical Faculty of IT and Design"],"affiliations":[{"raw_affiliation_string":"The Technical Faculty of IT and Design","institution_ids":["https://openalex.org/I4210134959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063946978","display_name":"Jesper Lisby H\u00f8jvang","orcid":"https://orcid.org/0009-0002-6278-9353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesper Lisby H\u00f8jvang","raw_affiliation_strings":["Capturi"],"affiliations":[{"raw_affiliation_string":"Capturi","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054964567","display_name":"Morten H\u00f8jfeldt Rasmussen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morten H\u00f8jfeldt Rasmussen","raw_affiliation_strings":["Capturi"],"affiliations":[{"raw_affiliation_string":"Capturi","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Audio Analysis Laboratory"],"affiliations":[{"raw_affiliation_string":"Audio Analysis Laboratory","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029253113"],"corresponding_institution_ids":["https://openalex.org/I4210133201"],"apc_list":null,"apc_paid":null,"fwci":1.5209,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8364288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2667","last_page":"2671"},"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":0.9991000294685364,"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/T13289","display_name":"Infant Health and Development","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.7704983353614807},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7118982076644897},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6861324310302734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6043619513511658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5580673217773438},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5421936511993408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4481189250946045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42988133430480957},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.11413565278053284},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07087105512619019},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.051366329193115234}],"concepts":[{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.7704983353614807},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7118982076644897},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6861324310302734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6043619513511658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580673217773438},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5421936511993408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4481189250946045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42988133430480957},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.11413565278053284},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07087105512619019},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.051366329193115234},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1047","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/4f30e2af-47f8-4391-a33f-c3fdb40033b9","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/4f30e2af-47f8-4391-a33f-c3fdb40033b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Xiang, Y, Shi, L, Lisby H\u00f8jvang, J, H\u00f8jfeldt Rasmussen, M & Christensen, M G 2020, An NMF-HMM Speech Enhancement Method based on Kullback-Leibler Divergence. in Interspeech. pp. 2667-2671, Interspeech 2020, Shanghai, China, 25/10/2020. < https://indico2.conference4me.psnc.pl/event/35/contributions/3537/attachments/1043/1084/Wed-2-5-2.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/4f30e2af-47f8-4391-a33f-c3fdb40033b9","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/4f30e2af-47f8-4391-a33f-c3fdb40033b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Xiang, Y, Shi, L, Lisby H\u00f8jvang, J, H\u00f8jfeldt Rasmussen, M & Christensen, M G 2020, An NMF-HMM Speech Enhancement Method based on Kullback-Leibler Divergence. in Interspeech. pp. 2667-2671, Interspeech 2020, Shanghai, China, 25/10/2020. < https://indico2.conference4me.psnc.pl/event/35/contributions/3537/attachments/1043/1084/Wed-2-5-2.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1574263887","https://openalex.org/W1575431606","https://openalex.org/W1790748249","https://openalex.org/W1902027874","https://openalex.org/W1974387177","https://openalex.org/W1992475611","https://openalex.org/W1995536493","https://openalex.org/W2013608223","https://openalex.org/W2051428568","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2146544734","https://openalex.org/W2159514726","https://openalex.org/W2804690068","https://openalex.org/W2900450731","https://openalex.org/W2962866211","https://openalex.org/W3031135612"],"related_works":["https://openalex.org/W2037001019","https://openalex.org/W2136763963","https://openalex.org/W2105321464","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256"],"abstract_inverted_index":{"In":[0,91,104],"this":[1,95],"paper,":[2],"we":[3],"present":[4],"a":[5,108],"novel":[6,109],"supervised":[7],"Non-negative":[8],"Matrix<br/>Factorization":[9],"(NMF)":[10],"speech":[11,37,47,134,157],"enhancement":[12,48,158],"method,":[13],"which<br/>is":[14],"based":[15],"on":[16],"Hidden":[17],"Markov":[18],"Model":[19],"(HMM)":[20],"and":[21,89,136],"Kullback-<br/>Leibler":[22],"(KL)":[23],"divergence":[24],"(NMF-HMM).":[25],"Our":[26],"algorithm":[27],"applies<br/>theHMMto":[28],"capture":[29],"the":[30,34,51,57,63,73,78,83,92,101,105,116,126,144],"timing":[31],"information,":[32],"so":[33],"temporal":[35],"dynamics<br/>of":[36],"signal":[38],"can":[39],"be":[40],"considered":[41],"by":[42,130],"comparing":[43],"with<br/>the":[44],"traditional":[45],"NMF-based":[46],"method.":[49],"More<br/>specifically,":[50],"sum":[52],"of":[53,77,125,133,147],"Poisson,":[54],"leading":[55],"to":[56,82,99,120,151],"KL":[58],"divergence<br/>measure,":[59],"is":[60,80,87,97,118,128,149],"used":[61],"as":[62],"observation":[64],"model":[65],"for":[66],"each":[67],"state":[68],"of<br/>HMM.":[69],"This":[70],"ensures":[71],"that":[72,114,143],"parameter":[74],"update":[75,85],"rule":[76],"proposed<br/>algorithm":[79,127],"identical":[81],"multiplicative":[84],"rule,<br/>which":[86],"quick":[88],"efficient.":[90],"training":[93],"stage,":[94],"update<br/>rule":[96],"applied":[98],"train":[100],"NMF-HMM":[102,117],"model.":[103],"online":[106],"enhancement<br/>stage,":[107],"minimum":[110],"mean-square":[111],"error":[112],"(MMSE)<br/>estimator":[113],"combines":[115],"proposed":[119],"conduct<br/>speech":[121],"enhancement.":[122],"The":[123],"performance":[124],"evaluated":[129],"perceptual":[131],"evaluation":[132],"quality<br/>(PESQ)":[135],"short-timeobjective":[137],"intelligibility":[138],"(STOI).":[139],"The<br/>experimental":[140],"results":[141],"indicate":[142],"STOI":[145],"score":[146],"proposed<br/>strategy":[148],"able":[150],"outperform":[152],"7%":[153],"than":[154],"current":[155],"state-of-the-art<br/>NMF-based":[156],"methods.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}