{"id":"https://openalex.org/W3193846000","doi":"https://doi.org/10.21437/interspeech.2021-142","title":"Ultra Fast Speech Separation Model with Teacher Student Learning","display_name":"Ultra Fast Speech Separation Model with Teacher Student Learning","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3193846000","doi":"https://doi.org/10.21437/interspeech.2021-142","mag":"3193846000"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-142","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.12777","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sanyuan Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620750","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0003-0661-3628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072540013","display_name":"Xiangzhan Yu","orcid":"https://orcid.org/0000-0002-1183-2844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangzhan Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5079533447"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8468,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86054627,"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":"3026","last_page":"3030"},"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":0.9997000098228455,"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":0.9994999766349792,"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":0.7437638640403748},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7046736478805542},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6329262256622314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5323667526245117},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5084928274154663},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4367508292198181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319967031478882},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11210504174232483},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08826974034309387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437638640403748},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7046736478805542},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6329262256622314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5323667526245117},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5084928274154663},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4367508292198181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319967031478882},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11210504174232483},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08826974034309387},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-142","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.12777","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.12777","pdf_url":"https://arxiv.org/pdf/2204.12777","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.12777","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.12777","pdf_url":"https://arxiv.org/pdf/2204.12777","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2069681747","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2892009249","https://openalex.org/W2908510526","https://openalex.org/W2962982474","https://openalex.org/W2963458655","https://openalex.org/W2963925437","https://openalex.org/W2970454332","https://openalex.org/W2992632249","https://openalex.org/W2995181338","https://openalex.org/W3015834770","https://openalex.org/W3016232124","https://openalex.org/W3095311338","https://openalex.org/W3104215796"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2132885390","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"Transformer":[0,20,42,68,113],"has":[1],"been":[2],"successfully":[3],"applied":[4],"to":[5,22,28,57,72,94,100],"speech":[6,66,138,146,151],"separation":[7,67,139,152],"recently":[8],"with":[9,44,79,110],"its":[10,35],"strong":[11],"long-dependency":[12],"modeling":[13],"capacity":[14],"using":[15],"a":[16],"self-attention":[17],"mechanism.":[18],"However,":[19],"tends":[21],"have":[23],"heavy":[24],"run-time":[25],"costs":[26],"due":[27],"the":[29,96,105,111,118,124],"deep":[30],"encoder":[31,46],"layers,":[32],"which":[33],"hinders":[34],"deployment":[36],"on":[37,140],"edge":[38],"devices.":[39],"A":[40],"small":[41,97,112],"model":[43,69,99,114],"fewer":[45],"layers":[47],"is":[48,55,70],"preferred":[49],"for":[50,133],"computational":[51],"efficiency,":[52],"but":[53],"it":[54],"prone":[56],"performance":[58,76],"degradation.":[59],"In":[60],"this":[61],"paper,":[62],"an":[63],"ultra":[64,149],"fast":[65,150],"proposed":[71,119],"achieve":[73,154],"both":[74,134],"better":[75],"and":[77,90,136],"efficiency":[78],"teacher":[80,107],"student":[81,98],"learning":[82,89,121],"(T-S":[83],"learning).":[84],"We":[85],"introduce":[86],"layer-wise":[87],"T-S":[88,120],"objective":[91],"shifting":[92],"mechanisms":[93],"guide":[95],"learn":[101],"intermediate":[102],"representations":[103],"from":[104,116],"large":[106],"model.":[108],"Compared":[109],"trained":[115],"scratch,":[117],"method":[122],"reduces":[123],"word":[125],"error":[126],"rate":[127],"(WER)":[128],"by":[129],"more":[130,144,155],"than":[131,156],"5%":[132],"multi-channel":[135],"single-channel":[137],"LibriCSS":[141],"dataset.":[142],"Utilizing":[143],"unlabeled":[145],"data,":[147],"our":[148],"models":[153],"10%":[157],"relative":[158],"WER":[159],"reduction.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}