{"id":"https://openalex.org/W4372267368","doi":"https://doi.org/10.1109/icassp49357.2023.10094718","title":"Time-Domain Speech Enhancement Assisted by Multi-Resolution Frequency Encoder and Decoder","display_name":"Time-Domain Speech Enhancement Assisted by Multi-Resolution Frequency Encoder and Decoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267368","doi":"https://doi.org/10.1109/icassp49357.2023.10094718"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094718","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/A5078144636","display_name":"Hao Shi","orcid":"https://orcid.org/0000-0003-1974-8361"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hao Shi","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078144636"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":3.5319,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93772803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.9979000091552734,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761596143245697},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7424291968345642},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7218948602676392},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6964103579521179},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.6583805680274963},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.580077052116394},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5682024359703064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5621616840362549},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.5512250661849976},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5478779673576355},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.48212122917175293},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3879110813140869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3837664723396301},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35338595509529114},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.2811357080936432},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.2756020426750183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1609521508216858},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15897205471992493},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15484142303466797},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.14106425642967224},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09731021523475647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761596143245697},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7424291968345642},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7218948602676392},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6964103579521179},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.6583805680274963},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.580077052116394},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5682024359703064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5621616840362549},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.5512250661849976},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5478779673576355},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.48212122917175293},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3879110813140869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3837664723396301},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35338595509529114},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2811357080936432},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2756020426750183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1609521508216858},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15897205471992493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15484142303466797},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.14106425642967224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09731021523475647},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/icassp49357.2023.10094718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094718","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":51,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1920160043","https://openalex.org/W1972475755","https://openalex.org/W1984446451","https://openalex.org/W1992475611","https://openalex.org/W2001848432","https://openalex.org/W2044893557","https://openalex.org/W2050151235","https://openalex.org/W2051057783","https://openalex.org/W2054566816","https://openalex.org/W2094721231","https://openalex.org/W2096779346","https://openalex.org/W2120847449","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2166841940","https://openalex.org/W2290318471","https://openalex.org/W2802304149","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2943554574","https://openalex.org/W2949558265","https://openalex.org/W2963341071","https://openalex.org/W2971758476","https://openalex.org/W2998161426","https://openalex.org/W2998832642","https://openalex.org/W3015338123","https://openalex.org/W3015912787","https://openalex.org/W3017350693","https://openalex.org/W3032514799","https://openalex.org/W3096408984","https://openalex.org/W3096641561","https://openalex.org/W3097945073","https://openalex.org/W3102190437","https://openalex.org/W3211438798","https://openalex.org/W4221156109","https://openalex.org/W4223945715","https://openalex.org/W4289242435","https://openalex.org/W4297841603","https://openalex.org/W4372266968","https://openalex.org/W4382202533","https://openalex.org/W6639824700","https://openalex.org/W6676284021","https://openalex.org/W6756251360","https://openalex.org/W6762114000","https://openalex.org/W6803744562","https://openalex.org/W6846626936","https://openalex.org/W6996806968"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2288135719","https://openalex.org/W3016109656","https://openalex.org/W2533590149","https://openalex.org/W2381036744","https://openalex.org/W2323749021","https://openalex.org/W2901989338","https://openalex.org/W4381416811","https://openalex.org/W2909460703"],"abstract_inverted_index":{"Time-domain":[0],"speech":[1],"enhancement":[2],"(SE)":[3],"has":[4],"recently":[5],"been":[6],"intensively":[7],"investigated.":[8],"Among":[9],"recent":[10],"works,":[11],"DEMUCS":[12],"[1]":[13],"introduces":[14],"multi-resolution":[15,36,48],"STFT":[16,26],"loss":[17,117],"to":[18,34,97],"enhance":[19],"performance.":[20,119],"However,":[21],"some":[22],"resolutions":[23],"used":[24],"for":[25],"contain":[27],"non-stationary":[28,103],"signals,":[29],"and":[30,71,108],"it":[31,93],"is":[32,94],"challenging":[33],"learn":[35],"frequency":[37,49,66,86,100,116],"losses":[38],"simultaneously":[39],"with":[40,114],"only":[41],"one":[42],"output.":[43],"For":[44],"better":[45],"use":[46],"of":[47,80],"information,":[50],"we":[51],"supplement":[52],"multiple":[53,76,111],"spectrograms":[54],"in":[55,68,105],"different":[56],"frame":[57],"lengths":[58],"into":[59],"the":[60,106,110,115,122,127],"time-domain":[61],"encoders.":[62],"They":[63],"extract":[64],"stationary":[65,99],"information":[67],"both":[69],"narrowband":[70],"wideband.":[72],"We":[73],"also":[74],"adopt":[75],"decoder":[77],"outputs,":[78],"each":[79],"which":[81],"computes":[82],"its":[83],"corresponding":[84],"resolution":[85],"loss.":[87],"Experimental":[88],"results":[89],"show":[90,125],"that":[91,126],"(1)":[92],"more":[95],"effective":[96],"fuse":[98],"features":[101,104],"than":[102],"encoder,":[107],"(2)":[109],"outputs":[112],"consistent":[113],"improve":[118],"Experiments":[120],"on":[121],"Voice-Bank":[123],"dataset":[124],"proposed":[128],"method":[129],"obtained":[130],"a":[131],"0.14":[132],"PESQ":[133],"improvement.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}