{"id":"https://openalex.org/W2901439043","doi":"https://doi.org/10.1109/icassp.2019.8682830","title":"Using Recurrences in Time and Frequency within U-net Architecture for Speech Enhancement","display_name":"Using Recurrences in Time and Frequency within U-net Architecture for Speech Enhancement","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2901439043","doi":"https://doi.org/10.1109/icassp.2019.8682830","mag":"2901439043"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.06805","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045397888","display_name":"Tomasz Grzywalski","orcid":"https://orcid.org/0000-0002-9388-0494"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tomasz Grzywalski","raw_affiliation_strings":["StethoMe, Poznan, Poland","StethoMe\u00ae, Poznan, Poland"],"affiliations":[{"raw_affiliation_string":"StethoMe, Poznan, Poland","institution_ids":[]},{"raw_affiliation_string":"StethoMe\u00ae, Poznan, Poland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054280374","display_name":"Szymon Drgas","orcid":"https://orcid.org/0000-0002-4603-8894"},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Szymon Drgas","raw_affiliation_strings":["Institute of Automation and Robotics, Poznan University of Technology, Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Automation and Robotics, Poznan University of Technology, Poland","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045397888"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00488162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":null,"first_page":"6970","last_page":"6974"},"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":0.9994999766349792,"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":0.9991999864578247,"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":0.6783691644668579},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6543174982070923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6452102661132812},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5943399667739868},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5874432325363159},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5810138583183289},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.44126713275909424},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.43382734060287476},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3230653405189514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30258166790008545},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22587820887565613},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.17381635308265686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1538611650466919},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09039545059204102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783691644668579},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6543174982070923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6452102661132812},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5943399667739868},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5874432325363159},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5810138583183289},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.44126713275909424},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.43382734060287476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3230653405189514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30258166790008545},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22587820887565613},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.17381635308265686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1538611650466919},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09039545059204102},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.06805","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06805","pdf_url":"https://arxiv.org/pdf/1811.06805","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"},{"id":"mag:2901439043","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.06805","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1811.06805","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.06805","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.06805","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06805","pdf_url":"https://arxiv.org/pdf/1811.06805","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":[{"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/W2901439043.pdf","grobid_xml":"https://content.openalex.org/works/W2901439043.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1664573881","https://openalex.org/W1790748249","https://openalex.org/W1901129140","https://openalex.org/W2031647436","https://openalex.org/W2069681747","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2285420822","https://openalex.org/W2526733715","https://openalex.org/W2605138598","https://openalex.org/W2618099328","https://openalex.org/W2678916739","https://openalex.org/W2783473931","https://openalex.org/W2789131247","https://openalex.org/W2793389773","https://openalex.org/W2904648837","https://openalex.org/W2952367144","https://openalex.org/W2962843322","https://openalex.org/W2962866211","https://openalex.org/W3127686677","https://openalex.org/W6637116368","https://openalex.org/W6639824700","https://openalex.org/W6728226663","https://openalex.org/W6746914816","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W3088775906","https://openalex.org/W3015797583","https://openalex.org/W3011129471","https://openalex.org/W2963828919","https://openalex.org/W3174609245","https://openalex.org/W3134064908","https://openalex.org/W2786835328","https://openalex.org/W2915844545","https://openalex.org/W2363736995","https://openalex.org/W1990155902","https://openalex.org/W3108487808","https://openalex.org/W3108010525","https://openalex.org/W3113031658","https://openalex.org/W2403766732","https://openalex.org/W3028077980","https://openalex.org/W3011475824","https://openalex.org/W2889669262","https://openalex.org/W2941484407","https://openalex.org/W2740916758","https://openalex.org/W2801068874"],"abstract_inverted_index":{"When":[0],"designing":[1],"fully-convolutional":[2],"neural":[3],"network,":[4],"there":[5],"is":[6],"a":[7,32],"trade-off":[8],"between":[9],"receptive":[10],"field":[11],"size,":[12],"number":[13],"of":[14,19,24,39,89,94],"parameters":[15],"and":[16,42,61,85,101],"spatial":[17],"resolution":[18],"features":[20],"in":[21,92],"deeper":[22],"layers":[23,44],"the":[25,59,109],"network.":[26],"In":[27],"this":[28],"work":[29],"we":[30],"present":[31],"novel":[33],"network":[34],"design":[35],"based":[36,55],"on":[37,65,73],"combination":[38],"many":[40],"convolutional":[41],"recurrent":[43],"that":[45],"solves":[46],"these":[47],"dilemmas.":[48],"We":[49,69],"compare":[50],"our":[51,71],"solution":[52,72,91],"with":[53,78],"U-nets":[54],"models":[56,64],"known":[57],"from":[58,82],"literature":[60],"other":[62],"baseline":[63],"speech":[66,75],"enhancement":[67],"task.":[68],"test":[70],"TIMIT":[74],"utterances":[76],"combined":[77],"noise":[79],"segments":[80],"extracted":[81],"NOISEX-92":[83],"database":[84],"show":[86],"clear":[87],"advantage":[88],"proposed":[90],"terms":[93],"SDR":[95],"(signal-to-distortion":[96],"ratio),":[97],"SIR":[98],"(signal-to-interference":[99],"ratio)":[100],"STOI":[102],"(spectro-temporal":[103],"objective":[104],"intelligibility)":[105],"metrics":[106],"compared":[107],"to":[108],"current":[110],"state-of-the-art.":[111]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}