{"id":"https://openalex.org/W3016267250","doi":"https://doi.org/10.1109/icassp40776.2020.9054196","title":"DNN-Based Speech Presence Probability Estimation for Multi-Frame Single-Microphone Speech Enhancement","display_name":"DNN-Based Speech Presence Probability Estimation for Multi-Frame Single-Microphone Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016267250","doi":"https://doi.org/10.1109/icassp40776.2020.9054196","mag":"3016267250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.08492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068315029","display_name":"Marvin Tammen","orcid":"https://orcid.org/0000-0002-7216-2717"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marvin Tammen","raw_affiliation_strings":["Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086003532","display_name":"D\u00f6rte Fischer","orcid":"https://orcid.org/0000-0003-3736-4441"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorte Fischer","raw_affiliation_strings":["Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":["Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068315029"],"corresponding_institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":2.5908,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90304854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"195"},"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":0.998199999332428,"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":0.988099992275238,"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/speech-enhancement","display_name":"Speech enhancement","score":0.8993992805480957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262387275695801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6585684418678284},{"id":"https://openalex.org/keywords/inter-frame","display_name":"Inter frame","score":0.6059802770614624},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5955125093460083},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5397295951843262},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5154367685317993},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.5011887550354004},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47786396741867065},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4606793522834778},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45197176933288574},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4511517584323883},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.433843731880188},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43074822425842285},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.366106241941452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3180696368217468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2234272062778473},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12982162833213806},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09796345233917236},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.0816887617111206},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07284972071647644}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8993992805480957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262387275695801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6585684418678284},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.6059802770614624},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5955125093460083},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5397295951843262},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5154367685317993},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.5011887550354004},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47786396741867065},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4606793522834778},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45197176933288574},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4511517584323883},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.433843731880188},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43074822425842285},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.366106241941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3180696368217468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2234272062778473},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12982162833213806},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09796345233917236},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.0816887617111206},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07284972071647644},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.08492","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.08492","pdf_url":"https://arxiv.org/pdf/1905.08492","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.08492","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.08492","pdf_url":"https://arxiv.org/pdf/1905.08492","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1836465849","https://openalex.org/W1891272442","https://openalex.org/W1897240248","https://openalex.org/W1974387177","https://openalex.org/W1999405021","https://openalex.org/W2024490156","https://openalex.org/W2037951967","https://openalex.org/W2051428568","https://openalex.org/W2060108923","https://openalex.org/W2069681747","https://openalex.org/W2075098731","https://openalex.org/W2079735306","https://openalex.org/W2106272332","https://openalex.org/W2118354544","https://openalex.org/W2120608389","https://openalex.org/W2121973264","https://openalex.org/W2127292597","https://openalex.org/W2135284480","https://openalex.org/W2146324387","https://openalex.org/W2151484683","https://openalex.org/W2291877678","https://openalex.org/W2398042854","https://openalex.org/W2620758562","https://openalex.org/W2734774145","https://openalex.org/W2763411440","https://openalex.org/W2766876424","https://openalex.org/W2775477443","https://openalex.org/W2891759647","https://openalex.org/W2899771611","https://openalex.org/W2899963229","https://openalex.org/W2918296821","https://openalex.org/W2949117887","https://openalex.org/W2964121744","https://openalex.org/W2985383517","https://openalex.org/W3147539069","https://openalex.org/W4214498238","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6638667902","https://openalex.org/W6738729105","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2028846388","https://openalex.org/W2072015625","https://openalex.org/W4295210860","https://openalex.org/W2438843077","https://openalex.org/W2161534637","https://openalex.org/W2010870899","https://openalex.org/W3168171120","https://openalex.org/W2393227939"],"abstract_inverted_index":{"Multi-frame":[0],"approaches":[1,26,38],"for":[2,109,123],"single-microphone":[3],"speech":[4,16,47,61,80,150],"enhancement,":[5],"e.g.,":[6],"the":[7,29,55,60,72,79,107,119,137,142,168,175],"multi-frame":[8,37],"minimum-power-distortionless-response":[9],"(MFMPDR)":[10],"filter,":[11],"are":[12],"able":[13],"to":[14,24,94,105,153,174],"exploit":[15],"correlations":[17,166],"across":[18],"neighboring":[19],"time":[20],"frames.":[21],"In":[22,89],"contrast":[23],"single-frame":[25],"such":[27],"as":[28],"Wiener":[30,176],"gain,":[31],"it":[32,160],"has":[33],"been":[34],"shown":[35],"that":[36,50,136,163],"achieve":[39],"a":[40,96,116,129,154],"substantial":[41],"noise":[42,125],"reduction":[43],"with":[44,141],"hardly":[45],"any":[46],"distortion,":[48],"provided":[49],"an":[51,76,148],"accurate":[52],"estimate":[53,77,106],"of":[54,71,78],"correlation":[56,63],"matrices":[57],"and":[58,127],"especially":[59,178],"interframe":[62,165],"(IFC)":[64],"vector":[65,74],"is":[66,121,161,170],"available.":[67],"Typical":[68],"estimation":[69],"procedures":[70],"IFC":[73],"require":[75],"presence":[81],"probability":[82],"(SPP)":[83],"in":[84,139,167,179],"each":[85,110],"time-frequency":[86],"(TF)":[87],"bin.":[88,112],"this":[90],"paper,":[91],"we":[92],"propose":[93],"use":[95],"bi-directional":[97],"long":[98],"short-term":[99],"memory":[100],"deep":[101],"neural":[102],"network":[103],"(DNN)":[104],"SPP":[108,145,157],"TF":[111],"Aiming":[113],"at":[114],"achieving":[115],"robust":[117],"performance,":[118],"DNN":[120],"trained":[122],"various":[124],"types":[126],"within":[128],"large":[130],"signal-to-noise-ratio":[131],"range.":[132],"Experimental":[133],"results":[134],"show":[135],"MFMPDR":[138,169],"combination":[140],"proposed":[143],"data-driven":[144],"estimator":[146],"yields":[147],"increased":[149],"quality":[151],"compared":[152,173],"state-of-the-art":[155],"model-based":[156],"estimator.":[158],"Furthermore,":[159],"confirmed":[162],"exploiting":[164],"beneficial":[171],"when":[172],"gain":[177],"adverse":[180],"scenarios.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2020-04-17T00:00:00"}