{"id":"https://openalex.org/W4375868852","doi":"https://doi.org/10.1109/icassp49357.2023.10096321","title":"Frequency Bin-Wise Single Channel Speech Presence Probability Estimation Using Multiple DNNS","display_name":"Frequency Bin-Wise Single Channel Speech Presence Probability Estimation Using Multiple DNNS","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868852","doi":"https://doi.org/10.1109/icassp49357.2023.10096321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096321","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.12048.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007499353","display_name":"Shuai Tao","orcid":"https://orcid.org/0000-0003-2223-0205"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Shuai Tao","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078791449","display_name":"Himavanth Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Himavanth Reddy","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041263382","display_name":"Jesper Rindom Jensen","orcid":"https://orcid.org/0000-0001-6023-8270"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Rindom Jensen","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"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/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab, CREATE,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9238,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73319302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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":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":0.9990000128746033,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.6126765608787537},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.6106473207473755},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5539339780807495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5508551001548767},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.48784923553466797},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32078850269317627},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.216183602809906},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10251614451408386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126765608787537},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.6106473207473755},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5539339780807495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5508551001548767},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.48784923553466797},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32078850269317627},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.216183602809906},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10251614451408386},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096321","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/11bb5a28-a0cf-4f10-995b-0ec6d600efac","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/11bb5a28-a0cf-4f10-995b-0ec6d600efac","pdf_url":"https://arxiv.org/pdf/2302.12048.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tao, S, Reddy, H, Jensen, J R & Christensen, M G 2023, Frequency bin-wise single channel speech presence probability estimation using multiple DNNs. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 10096321, IEEE (Institute of Electrical and Electronics Engineers), I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 1-5, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023, Rhodes Island, Greece, 04/06/2023. https://doi.org/10.1109/ICASSP49357.2023.10096321","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/11bb5a28-a0cf-4f10-995b-0ec6d600efac","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/11bb5a28-a0cf-4f10-995b-0ec6d600efac","pdf_url":"https://arxiv.org/pdf/2302.12048.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tao, S, Reddy, H, Jensen, J R & Christensen, M G 2023, Frequency bin-wise single channel speech presence probability estimation using multiple DNNs. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 10096321, IEEE (Institute of Electrical and Electronics Engineers), I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 1-5, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023, Rhodes Island, Greece, 04/06/2023. https://doi.org/10.1109/ICASSP49357.2023.10096321","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375868852.pdf","grobid_xml":"https://content.openalex.org/works/W4375868852.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W1924770834","https://openalex.org/W1975301756","https://openalex.org/W2033875152","https://openalex.org/W2040909219","https://openalex.org/W2044893557","https://openalex.org/W2051428568","https://openalex.org/W2069681747","https://openalex.org/W2120608389","https://openalex.org/W2127292597","https://openalex.org/W2146324387","https://openalex.org/W2154890045","https://openalex.org/W2155998647","https://openalex.org/W2157995113","https://openalex.org/W2507424718","https://openalex.org/W2593116425","https://openalex.org/W2896457183","https://openalex.org/W2962892438","https://openalex.org/W2963458655","https://openalex.org/W2972592847","https://openalex.org/W3015969340","https://openalex.org/W3016267250","https://openalex.org/W3017350693","https://openalex.org/W3038205844","https://openalex.org/W3147539069","https://openalex.org/W3161950572","https://openalex.org/W3165776651","https://openalex.org/W3202568477","https://openalex.org/W4225905067","https://openalex.org/W4232282348","https://openalex.org/W4285115638","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2107701374","https://openalex.org/W1616588898","https://openalex.org/W4395000504","https://openalex.org/W4249504934","https://openalex.org/W2183416055","https://openalex.org/W2568867011","https://openalex.org/W1994114538","https://openalex.org/W2413205705","https://openalex.org/W2735644334","https://openalex.org/W138879321"],"abstract_inverted_index":{"In":[0,83],"this":[1],"work,":[2],"we":[3,62,125,132],"propose":[4],"a":[5,64,90],"frequency":[6,31,66,73,128],"bin-wise":[7,129],"method":[8,138],"to":[9,77,97],"estimate":[10],"the":[11,24,52,56,59,85,89,106,117,127,142],"single-channel":[12],"speech":[13,87,118,150],"presence":[14],"probability":[15,92],"(SPP)":[16],"with":[17],"multiple":[18],"deep":[19],"neural":[20],"networks":[21],"(DNNs)":[22],"in":[23,147],"short-time":[25],"Fourier":[26],"transform":[27],"domain.":[28],"Since":[29],"all":[30],"bins":[32,74],"are":[33,95],"typically":[34],"considered":[35],"simultaneously":[36],"as":[37],"input":[38],"features":[39],"for":[40],"conventional":[41],"DNN-based":[42],"SPP":[43,93,144],"estimators,":[44],"high":[45],"model":[46,53,154],"complexity":[47,54],"is":[48],"inevitable.":[49],"To":[50],"reduce":[51],"and":[55,68,88,153],"requirements":[57],"on":[58,105],"training":[60],"data,":[61],"take":[63],"single":[65],"bin":[67],"some":[69],"of":[70,141,149],"its":[71],"neighboring":[72],"into":[75],"account":[76],"train":[78,98],"separate":[79],"gate":[80],"recurrent":[81],"units.":[82],"addition,":[84],"noisy":[86],"posteriori":[91],"representation":[94],"used":[96],"our":[99,136],"model.":[100,130],"The":[101,112],"experiments":[102],"were":[103],"performed":[104],"Deep":[107],"Noise":[108],"Suppression":[109],"challenge":[110],"dataset.":[111],"experimental":[113],"results":[114],"show":[115],"that":[116,135],"detection":[119,151],"accuracy":[120,152],"can":[121],"be":[122],"improved":[123],"when":[124],"employ":[126],"Finally,":[131],"also":[133],"demonstrate":[134],"proposed":[137],"outperforms":[139],"most":[140],"state-of-the-art":[143],"estimation":[145],"methods":[146],"terms":[148],"complexity.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
