{"id":"https://openalex.org/W4388821133","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317310","title":"ScaleFormer: Transformer-based speech enhancement in the multi-scale time domain","display_name":"ScaleFormer: Transformer-based speech enhancement in the multi-scale time domain","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821133","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317310"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317310","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5045476493","display_name":"Tianci Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianci Wu","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103195569","display_name":"Shulin He","orcid":"https://orcid.org/0009-0002-0382-3515"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685573","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0001-5382-8467"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XueLiang Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"2448","last_page":"2453"},"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":0.9965000152587891,"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/transformer","display_name":"Transformer","score":0.7088810205459595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7063708305358887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5379209518432617},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4978642463684082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44115450978279114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3846685588359833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12462586164474487},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09212443232536316}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7088810205459595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063708305358887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5379209518432617},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4978642463684082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44115450978279114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3846685588359833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12462586164474487},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09212443232536316},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317310","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1606614440","https://openalex.org/W2024490156","https://openalex.org/W2070126272","https://openalex.org/W2141998673","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2529093176","https://openalex.org/W2889442120","https://openalex.org/W2897371647","https://openalex.org/W2937484199","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2972948005","https://openalex.org/W2991361823","https://openalex.org/W3015197852","https://openalex.org/W3015199127","https://openalex.org/W3095820034","https://openalex.org/W3096408984","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3158779859","https://openalex.org/W3163652268","https://openalex.org/W4225309689","https://openalex.org/W6631190155","https://openalex.org/W6656414902"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Processing":[0],"speech":[1,12,23,40],"at":[2,41],"multiple":[3,42,92],"temporal":[4,43,58],"scales":[5],"greatly":[6],"improves":[7],"the":[8,69,76,79,89,113,116],"performance":[9],"of":[10,78,132],"automatic":[11],"recognition,":[13],"but":[14],"its":[15],"effect":[16],"has":[17],"not":[18],"been":[19],"fully":[20],"exploited":[21],"in":[22,97,130],"enhancement":[24],"tasks.":[25],"In":[26,45],"this":[27],"study,":[28],"we":[29,47],"propose":[30],"a":[31,102],"novel":[32],"Transformer-based":[33],"neural":[34],"network":[35],"termed":[36],"ScaleFormer,":[37,46],"which":[38],"analyzes":[39],"resolutions.":[44],"utilize":[48],"an":[49,62,82],"encoder":[50],"that":[51,123],"employs":[52],"multi-scale":[53],"convolution":[54],"to":[55,67,87,105],"extract":[56,68],"different":[57],"scale":[59],"features.":[60],"Then,":[61],"intra-scale":[63,80],"transformer":[64,84,95],"is":[65,85,99],"used":[66,86],"representation":[70],"within":[71],"each":[72],"scale.":[73],"After":[74],"obtaining":[75],"output":[77],"transformer,":[81],"inter-scale":[83],"model":[88],"relationship":[90],"between":[91],"scales.":[93],"All":[94],"block":[96],"ScaleFormer":[98],"designed":[100],"with":[101],"dual-path":[103],"framework":[104],"learn":[106],"short":[107],"and":[108],"long-term":[109],"dependencies.":[110],"We":[111],"conduct":[112],"experiments":[114],"on":[115],"WSJ0":[117],"SI-84":[118],"corpus.":[119],"Experimental":[120],"results":[121],"show":[122],"our":[124],"approach":[125],"outperforms":[126],"previous":[127],"representative":[128],"systems":[129],"terms":[131],"objective":[133],"metrics.":[134]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}