{"id":"https://openalex.org/W3015794161","doi":"https://doi.org/10.1109/icassp40776.2020.9054719","title":"Mixup-breakdown: A Consistency Training Method for Improving Generalization of Speech Separation Models","display_name":"Mixup-breakdown: A Consistency Training Method for Improving Generalization of Speech Separation Models","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015794161","doi":"https://doi.org/10.1109/icassp40776.2020.9054719","mag":"3015794161"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5102313170","display_name":"Max W. Y. Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Max W. Y. Lam","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5728,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91567381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6374","last_page":"6378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/generalization","display_name":"Generalization","score":0.7751111388206482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7226245403289795},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.702811598777771},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6029984354972839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5073825716972351},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.46506837010383606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4262758791446686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32095807790756226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1414024531841278}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7751111388206482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226245403289795},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.702811598777771},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6029984354972839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5073825716972351},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.46506837010383606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262758791446686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32095807790756226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1414024531841278},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W830076066","https://openalex.org/W1494198834","https://openalex.org/W1983320747","https://openalex.org/W2029538739","https://openalex.org/W2086161653","https://openalex.org/W2099471712","https://openalex.org/W2099621636","https://openalex.org/W2148603752","https://openalex.org/W2221409856","https://openalex.org/W2407080277","https://openalex.org/W2431080869","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2592691248","https://openalex.org/W2604296437","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2765407302","https://openalex.org/W2770173563","https://openalex.org/W2800022361","https://openalex.org/W2889540509","https://openalex.org/W2891405874","https://openalex.org/W2892365986","https://openalex.org/W2951970475","https://openalex.org/W2952218014","https://openalex.org/W2952229419","https://openalex.org/W2953070460","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2963399829","https://openalex.org/W2963435192","https://openalex.org/W2963558289","https://openalex.org/W2964159205","https://openalex.org/W2964238697","https://openalex.org/W2973143779","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3137695714","https://openalex.org/W3209458476","https://openalex.org/W4238284510","https://openalex.org/W4320013936","https://openalex.org/W6623329352","https://openalex.org/W6629717138","https://openalex.org/W6675409298","https://openalex.org/W6688843265","https://openalex.org/W6713762819","https://openalex.org/W6717772578","https://openalex.org/W6733814495","https://openalex.org/W6736161267","https://openalex.org/W6745136726","https://openalex.org/W6746638498","https://openalex.org/W6763485134","https://openalex.org/W6764051988"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W3162204513","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2071676784","https://openalex.org/W2997094352","https://openalex.org/W4292513318","https://openalex.org/W3216976533","https://openalex.org/W2371138613"],"abstract_inverted_index":{"Deep-learning":[0],"based":[1,34],"speech":[2],"separation":[3],"models":[4,13],"confront":[5],"poor":[6],"generalization":[7,102],"problem":[8],"that":[9,114],"even":[10],"the":[11,53,68],"state-of-the-art":[12,105],"could":[14,71],"abruptly":[15],"fail":[16],"when":[17],"evaluating":[18],"them":[19],"in":[20],"mismatch":[21],"conditions.":[22],"To":[23],"address":[24],"this":[25],"problem,":[26],"we":[27,81],"propose":[28],"an":[29],"easy-to-implement":[30],"yet":[31],"effective":[32],"consistency":[33,69],"semi-supervised":[35],"learning":[36,74,107],"(SSL)":[37],"approach,":[38],"namely":[39],"Mixup-Breakdown":[40],"training":[41,137],"(MBT).":[42],"It":[43],"learns":[44],"a":[45,75],"teacher":[46],"model":[47],"to":[48,58,123,135],"\"breakdown\"":[49],"unlabeled":[50],"inputs,":[51],"and":[52,97,99,108],"estimated":[54],"separations":[55],"are":[56],"interpolated":[57],"produce":[59],"more":[60],"useful":[61],"pseudo":[62],"\"mixup\"":[63],"input-output":[64],"pairs,":[65],"on":[66],"which":[67],"regularization":[70],"apply":[72],"for":[73],"student":[76],"model.":[77],"In":[78],"our":[79],"experiment,":[80],"evaluate":[82],"MBT":[83,115,129],"under":[84],"various":[85],"conditions":[86],"with":[87,121],"ascending":[88],"degrees":[89],"of":[90],"mismatch,":[91],"including":[92],"unseen":[93],"interfering":[94],"speech,":[95],"noise,":[96],"music,":[98],"compare":[100],"MBT\u2019s":[101],"capability":[103],"against":[104],"supervised":[106],"SSL":[109],"approaches.":[110],"The":[111],"result":[112],"indicates":[113],"significantly":[116],"outperforms":[117],"several":[118],"strong":[119],"baselines":[120],"up":[122],"13.77%":[124],"relative":[125],"SI-SNRi":[126],"improvement.":[127],"Moreover,":[128],"only":[130],"adds":[131],"negligible":[132],"computational":[133],"overhead":[134],"standard":[136],"schemes.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}