{"id":"https://openalex.org/W4372271367","doi":"https://doi.org/10.1109/icassp49357.2023.10094992","title":"TF-GRIDNET: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation","display_name":"TF-GRIDNET: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372271367","doi":"https://doi.org/10.1109/icassp49357.2023.10094992"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094992","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079440375","display_name":"Shukjae Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shukjae Choi","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc.,Seoul,Korea","Hyundai Motor Group and 42dot Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I197312522"]},{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017337548","display_name":"Younglo Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younglo Lee","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc.,Seoul,Korea","Hyundai Motor Group and 42dot Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I197312522"]},{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc.,Seoul,Korea","Hyundai Motor Group and 42dot Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I197312522"]},{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.9219,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.99628575,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7639584541320801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7052223086357117},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.568341851234436},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.540117621421814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4947027862071991},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4896607995033264},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44166314601898193},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4145023226737976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3708357810974121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3691127300262451},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14857155084609985}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7639584541320801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052223086357117},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.568341851234436},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.540117621421814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4947027862071991},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4896607995033264},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44166314601898193},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4145023226737976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3708357810974121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3691127300262451},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14857155084609985},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094992","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2774389566","https://openalex.org/W2889540509","https://openalex.org/W2891405874","https://openalex.org/W2900893004","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963189033","https://openalex.org/W2963317762","https://openalex.org/W2972460025","https://openalex.org/W2991361823","https://openalex.org/W2996969697","https://openalex.org/W3007256793","https://openalex.org/W3012897083","https://openalex.org/W3015199127","https://openalex.org/W3015794161","https://openalex.org/W3035268204","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3134695619","https://openalex.org/W3158779859","https://openalex.org/W3160903688","https://openalex.org/W3163652268","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W3197381252","https://openalex.org/W3197627016","https://openalex.org/W3201698955","https://openalex.org/W3203119473","https://openalex.org/W3215005424","https://openalex.org/W4200598930","https://openalex.org/W4210402803","https://openalex.org/W4224931672","https://openalex.org/W4224936432","https://openalex.org/W4283794752","https://openalex.org/W4295312788","https://openalex.org/W4296068589","https://openalex.org/W4296068774","https://openalex.org/W4297841651","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745149982","https://openalex.org/W6766978945","https://openalex.org/W6771792932","https://openalex.org/W6774995033","https://openalex.org/W6775369996","https://openalex.org/W6802205285"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W2017779656","https://openalex.org/W1518859147","https://openalex.org/W2001172292","https://openalex.org/W2169567031","https://openalex.org/W2045506488","https://openalex.org/W1849802015","https://openalex.org/W1983045063"],"abstract_inverted_index":{"We":[0],"propose":[1],"TF-GridNet,":[2],"a":[3,37,42,98,133],"novel":[4,99],"multi-path":[5,28],"deep":[6],"neural":[7],"network":[8],"(DNN)":[9],"operating":[10],"in":[11,21],"the":[12,65,72,87,110,125,129],"time-frequency":[13],"(T-F)":[14],"domain,":[15],"for":[16,53,93],"monaural":[17],"talker-independent":[18],"speaker":[19],"separation":[20],"anechoic":[22],"conditions.":[23],"The":[24,55],"model":[25,56,94],"stacks":[26],"several":[27],"blocks,":[29],"each":[30],"consisting":[31],"of":[32,71],"an":[33],"intra-frame":[34],"spectral":[35,62],"module,":[36,40,45],"sub-band":[38],"temporal":[39],"and":[41,49,67],"full-band":[43],"self-attention":[44],"to":[46,59,80,102,106,109],"leverage":[47],"local":[48],"global":[50],"spectro-temporal":[51],"information":[52],"separation.":[54],"is":[57],"trained":[58],"perform":[60],"complex":[61],"mapping,":[63],"where":[64],"real":[66],"imaginary":[68],"(RI)":[69],"components":[70],"input":[73,78,111],"mixture":[74],"are":[75],"stacked":[76],"as":[77],"features":[79],"predict":[81],"target":[82],"RI":[83],"components.":[84],"Besides":[85],"using":[86,114],"scale-invariant":[88],"signal-to-distortion":[89],"ratio":[90],"(SI-SDR)":[91],"loss":[92,100],"training,":[95],"we":[96,117],"include":[97],"term":[101],"encourage":[103],"separated":[104],"sources":[105],"add":[107],"up":[108],"mixture.":[112],"Without":[113],"dynamic":[115],"mixing,":[116],"obtain":[118],"23.4":[119],"dB":[120],"SI-SDR":[121],"improvement":[122],"(SI-SDRi)":[123],"on":[124],"WSJ0-2mix":[126],"dataset,":[127],"outperforming":[128],"previous":[130],"best":[131],"by":[132],"large":[134],"margin.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":26}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}