{"id":"https://openalex.org/W3160324929","doi":"https://doi.org/10.1109/icassp39728.2021.9413999","title":"A Flow-Based Neural Network for Time Domain Speech Enhancement","display_name":"A Flow-Based Neural Network for Time Domain Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160324929","doi":"https://doi.org/10.1109/icassp39728.2021.9413999","mag":"3160324929"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.09008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050706599","display_name":"M. Strauss","orcid":"https://orcid.org/0000-0003-0610-8250"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"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"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Strauss","raw_affiliation_strings":["International Audio Laboratories Erlangen, A joint institution of the Friedrich-Alexander-University Erlangen-N\u00fcrnberg (FAU) and Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, A joint institution of the Friedrich-Alexander-University Erlangen-N\u00fcrnberg (FAU) and Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022331149","display_name":"Bernd Edler","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"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"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Edler","raw_affiliation_strings":["International Audio Laboratories Erlangen, A joint institution of the Friedrich-Alexander-University Erlangen-N\u00fcrnberg (FAU) and Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, A joint institution of the Friedrich-Alexander-University Erlangen-N\u00fcrnberg (FAU) and Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.622,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95152603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5754","last_page":"5758"},"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":0.9987999796867371,"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":0.995199978351593,"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":0.7878479957580566},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7463414072990417},{"id":"https://openalex.org/keywords/companding","display_name":"Companding","score":0.6642168760299683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5950562357902527},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5023868083953857},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4656204879283905},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4627893269062042},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4484902024269104},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4156706929206848},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4109213352203369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3721822500228882},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1301679015159607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10799944400787354},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0787748396396637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878479957580566},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7463414072990417},{"id":"https://openalex.org/C104250799","wikidata":"https://www.wikidata.org/wiki/Q1780765","display_name":"Companding","level":4,"score":0.6642168760299683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5950562357902527},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5023868083953857},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4656204879283905},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4627893269062042},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4484902024269104},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4156706929206848},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4109213352203369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3721822500228882},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1301679015159607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10799944400787354},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0787748396396637},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.09008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.09008","pdf_url":"https://arxiv.org/pdf/2106.09008","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2106.09008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.09008","pdf_url":"https://arxiv.org/pdf/2106.09008","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W17035842","https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1983108229","https://openalex.org/W1995536493","https://openalex.org/W2044893557","https://openalex.org/W2094721231","https://openalex.org/W2096779346","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2284050935","https://openalex.org/W2403555780","https://openalex.org/W2409550820","https://openalex.org/W2514828952","https://openalex.org/W2531409750","https://openalex.org/W2560747691","https://openalex.org/W2747161606","https://openalex.org/W2802304149","https://openalex.org/W2901861095","https://openalex.org/W2912298597","https://openalex.org/W2943237054","https://openalex.org/W2949558265","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2963341071","https://openalex.org/W2963685250","https://openalex.org/W2964121744","https://openalex.org/W2972443522","https://openalex.org/W2972466499","https://openalex.org/W2972516210","https://openalex.org/W2992005611","https://openalex.org/W2992035660","https://openalex.org/W2998678989","https://openalex.org/W2998832642","https://openalex.org/W2999160446","https://openalex.org/W3005621653","https://openalex.org/W3005914302","https://openalex.org/W3011982609","https://openalex.org/W3015219411","https://openalex.org/W3102190437","https://openalex.org/W3150807214","https://openalex.org/W4232282348","https://openalex.org/W4253928870","https://openalex.org/W4256607065","https://openalex.org/W4288089383","https://openalex.org/W4289761690","https://openalex.org/W4297798428","https://openalex.org/W6600710828","https://openalex.org/W6631190155","https://openalex.org/W6695676441","https://openalex.org/W6713425292","https://openalex.org/W6714644935","https://openalex.org/W6752910514","https://openalex.org/W6758706709","https://openalex.org/W6762114000","https://openalex.org/W6770847983","https://openalex.org/W6773094808","https://openalex.org/W6773419339"],"related_works":["https://openalex.org/W2141622453","https://openalex.org/W4297832041","https://openalex.org/W2034069800","https://openalex.org/W2366114306","https://openalex.org/W2942289697","https://openalex.org/W2165599567","https://openalex.org/W3045162464","https://openalex.org/W2132809008","https://openalex.org/W2362488330","https://openalex.org/W2389638540"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,59,84],"involves":[2],"the":[3,58,100,105,127],"distinction":[4],"of":[5,64,85,107],"a":[6,52,113],"target":[7],"speech":[8,66,77],"signal":[9],"from":[10,76],"an":[11],"intrusive":[12],"background.":[13],"Although":[14],"generative":[15],"approaches":[16],"using":[17,130],"Variational":[18],"Autoencoders":[19],"or":[20],"Generative":[21],"Adversarial":[22],"Networks":[23],"(GANs)":[24],"have":[25],"increasingly":[26],"been":[27],"used":[28],"in":[29,43,47,88],"recent":[30],"years,":[31],"normalizing":[32],"flow":[33],"(NF)":[34],"based":[35],"systems":[36],"are":[37],"still":[38],"scarse,":[39],"despite":[40],"their":[41,70],"success":[42],"related":[44],"fields.":[45],"Thus,":[46],"this":[48],"paper":[49],"we":[50,93],"propose":[51],"NF":[53],"framework":[54],"to":[55,81,120],"directly":[56],"model":[57,75,101],"process":[60],"by":[61,103],"density":[62],"estimation":[63],"clean":[65],"utterances":[67,87],"conditioned":[68],"on":[69,112],"noisy":[71,86],"counterpart.":[72],"The":[73],"WaveGlow":[74],"synthesis":[78],"is":[79],"adapted":[80],"enable":[82],"direct":[83],"time":[89],"domain.":[90],"In":[91],"addition,":[92],"demonstrate":[94],"that":[95],"nonlinear":[96],"input":[97,108],"companding":[98],"benefits":[99],"performance":[102],"equalizing":[104],"distribution":[106],"samples.":[109],"Experimental":[110],"evaluation":[111,132],"publicly":[114],"available":[115],"dataset":[116],"shows":[117],"comparable":[118],"results":[119],"current":[121],"state-of-the-art":[122],"GAN-based":[123],"approaches,":[124],"while":[125],"surpassing":[126],"chosen":[128],"baselines":[129],"objective":[131],"metrics.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}