{"id":"https://openalex.org/W4283727958","doi":"https://doi.org/10.21437/interspeech.2022-66","title":"Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation","display_name":"Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283727958","doi":"https://doi.org/10.21437/interspeech.2022-66"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-66","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-66","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100877748","display_name":"Jian Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luo","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077957584","display_name":"Edward Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2803097867","display_name":"Aquinas Institute of Theology","ror":"https://ror.org/029xxx628","country_code":"US","type":"education","lineage":["https://openalex.org/I2803097867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Xiao","raw_affiliation_strings":["Aquinas International Academy, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aquinas International Academy, CA, USA","institution_ids":["https://openalex.org/I2803097867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028437800","display_name":"Xulong Zhang","orcid":"https://orcid.org/0000-0001-7005-992X"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Xulong Zhang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5313","last_page":"5317"},"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":0.6319210529327393},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5253821611404419},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.42770904302597046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39177176356315613},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.25321972370147705},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.152847558259964},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08045992255210876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319210529327393},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5253821611404419},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42770904302597046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39177176356315613},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.25321972370147705},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.152847558259964},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08045992255210876},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-66","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-66","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320336405","display_name":"Special Project for Research and Development in Key areas of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2604869594","https://openalex.org/W2763421725","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2981436548","https://openalex.org/W2996428491","https://openalex.org/W3015199127","https://openalex.org/W3033529678","https://openalex.org/W3096893582","https://openalex.org/W3097201508","https://openalex.org/W3097777922","https://openalex.org/W3148040514","https://openalex.org/W3150269179","https://openalex.org/W3160864104","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3167533889","https://openalex.org/W3167946479","https://openalex.org/W3185109982","https://openalex.org/W3192610910","https://openalex.org/W3205879560","https://openalex.org/W4287812455","https://openalex.org/W4300943593","https://openalex.org/W4309793872","https://openalex.org/W4312510083"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Time-domain":[0],"Transformer":[1,40,63],"neural":[2],"networks":[3],"have":[4,15],"proven":[5],"their":[6],"superiority":[7],"in":[8],"speech":[9,43],"separation":[10,97],"tasks.However,":[11],"these":[12],"models":[13],"usually":[14],"a":[16,36],"large":[17],"number":[18],"of":[19,27,39],"network":[20,41],"parameters,":[21],"thus":[22],"often":[23],"encountering":[24],"the":[25,50,61,78,82,91],"problem":[26],"GPU":[28],"memory":[29,54],"explosion.In":[30],"this":[31],"paper,":[32],"we":[33],"proposed":[34],"Tiny-Sepformer,":[35],"tiny":[37],"version":[38],"for":[42],"separation.We":[44],"present":[45],"two":[46,65],"techniques":[47],"to":[48,64],"reduce":[49,90],"model":[51,92],"parameters":[52,80],"and":[53,69,94],"consumption:":[55],"(1)":[56],"Convolution-Attention":[57],"(CA)":[58],"block,":[59],"spliting":[60],"vanilla":[62,100],"paths,":[66],"multi-head":[67],"attention":[68],"1D":[70],"depthwise":[71],"separable":[72],"convolution,":[73],"(2)":[74],"parameter":[75],"sharing,":[76],"sharing":[77],"layer":[79],"within":[81],"CA":[83],"block.In":[84],"our":[85],"experiments,":[86],"Tiny-Sepformer":[87],"could":[88],"greatly":[89],"size,":[93],"achieves":[95],"comparable":[96],"performance":[98],"with":[99],"Sepformer":[101],"on":[102],"WSJ0-2/3Mix":[103],"datasets.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}