{"id":"https://openalex.org/W3162629387","doi":"https://doi.org/10.1109/icassp39728.2021.9413670","title":"TransMask: A Compact and Fast Speech Separation Model Based on Transformer","display_name":"TransMask: A Compact and Fast Speech Separation Model Based on Transformer","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162629387","doi":"https://doi.org/10.1109/icassp39728.2021.9413670","mag":"3162629387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5030460543","display_name":"Zining Zhang","orcid":"https://orcid.org/0000-0002-7992-426X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Zining Zhang","raw_affiliation_strings":["PVoice Technology Singapore","School of Computing, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"PVoice Technology Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["School of Computing, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633295","display_name":"Zhenjie Zhang","orcid":"https://orcid.org/0000-0003-2053-3771"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhenjie Zhang","raw_affiliation_strings":["PVoice Technology Singapore","School of Computing, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"PVoice Technology Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"School of Computing, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030460543"],"corresponding_institution_ids":["https://openalex.org/I165932596","https://openalex.org/I168639165"],"apc_list":null,"apc_paid":null,"fwci":2.3142,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88984751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5764","last_page":"5768"},"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":0.9994000196456909,"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":0.7997279167175293},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7257776856422424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6506741046905518},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5689350962638855},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5358513593673706},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46981576085090637},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46902599930763245},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4380251467227936},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4358684718608856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3406415581703186},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08213496208190918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997279167175293},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7257776856422424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6506741046905518},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5689350962638855},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5358513593673706},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46981576085090637},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46902599930763245},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4380251467227936},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4358684718608856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3406415581703186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08213496208190918},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/icassp39728.2021.9413670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2899663614","https://openalex.org/W2940744433","https://openalex.org/W2941814890","https://openalex.org/W2952218014","https://openalex.org/W2956480774","https://openalex.org/W2962935966","https://openalex.org/W2963403868","https://openalex.org/W2972460025","https://openalex.org/W2979636403","https://openalex.org/W2981857663","https://openalex.org/W3015199127","https://openalex.org/W3015468748","https://openalex.org/W3027008958","https://openalex.org/W3045904949","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W4287632494","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6761563299","https://openalex.org/W6761628794","https://openalex.org/W6765571568","https://openalex.org/W6768952226","https://openalex.org/W6776048684","https://openalex.org/W6777776875","https://openalex.org/W6782142667","https://openalex.org/W6784764134"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W1546240199","https://openalex.org/W2051376034","https://openalex.org/W3211091508","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W193702574","https://openalex.org/W72660888","https://openalex.org/W2089240210","https://openalex.org/W2063862874"],"abstract_inverted_index":{"Speech":[0],"separation":[1,38,66,74],"is":[2,95,103],"an":[3],"important":[4],"problem":[5],"in":[6],"speech":[7,16,22,37,47,73,137],"processing,":[8],"which":[9],"targets":[10],"to":[11],"separate":[12],"and":[13,60,100,119],"generate":[14],"clean":[15,46],"from":[17,23],"a":[18,70],"mixed":[19],"audio":[20,128,138],"containing":[21],"different":[24],"speakers.":[25],"Empowered":[26],"by":[27,55],"the":[28,57,81,91,101,115],"deep":[29],"learning":[30],"technologies":[31],"over":[32,144],"sequence-to-sequence":[33],"domain,":[34],"recent":[35],"neural":[36],"models":[39,52],"are":[40],"now":[41],"capable":[42],"of":[43,83,93],"generating":[44],"highly":[45],"audios.":[48],"To":[49],"make":[50],"these":[51],"more":[53,96,104],"practical":[54],"reducing":[56],"model":[58],"size":[59,92],"inference":[61,102,123],"time":[62,124],"while":[63],"maintaining":[64],"high":[65],"quality,":[67,139],"we":[68,89],"propose":[69],"new":[71],"transformer-based":[72],"approach,":[75],"called":[76],"TransMask.":[77],"By":[78],"fully":[79,113],"unleashing":[80],"power":[82],"self-attention":[84],"on":[85,135],"long-term":[86],"dependency":[87],"reception,":[88],"demonstrate":[90],"TransMask":[94,112],"than":[97,105,109],"60%":[98],"smaller":[99],"2":[106],"times":[107],"faster":[108],"state-of-the-art":[110],"solutions.":[111],"utilizes":[114],"parallelism":[116],"during":[117],"inference,":[118],"achieves":[120],"nearly":[121],"linear":[122],"within":[125],"reasonable":[126],"input":[127],"lengths.":[129],"It":[130],"also":[131],"outperforms":[132],"existing":[133],"solutions":[134],"output":[136],"achieving":[140],"SDR":[141],"above":[142],"16":[143],"Librimix":[145],"benchmark.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}