{"id":"https://openalex.org/W2963773971","doi":"https://doi.org/10.21437/interspeech.2017-305","title":"Recognizing Multi-Talker Speech with Permutation Invariant Training","display_name":"Recognizing Multi-Talker Speech with Permutation Invariant Training","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963773971","doi":"https://doi.org/10.21437/interspeech.2017-305","mag":"2963773971"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034476404"],"corresponding_institution_ids":["https://openalex.org/I58610484"],"apc_list":null,"apc_paid":null,"fwci":8.5227,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98063643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2456","last_page":"2460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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":0.9805999994277954,"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/invariant","display_name":"Invariant (physics)","score":0.6112102270126343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5702558159828186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.55875563621521},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4474775195121765},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44544166326522827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34471267461776733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23529192805290222},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09279832243919373},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08057704567909241}],"concepts":[{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6112102270126343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5702558159828186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.55875563621521},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4474775195121765},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44544166326522827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34471267461776733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23529192805290222},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09279832243919373},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08057704567909241},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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":30,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W330298975","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1995562189","https://openalex.org/W2060822897","https://openalex.org/W2119203697","https://openalex.org/W2144763279","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2193413348","https://openalex.org/W2198724430","https://openalex.org/W2208299922","https://openalex.org/W2221409856","https://openalex.org/W2292414329","https://openalex.org/W2394932179","https://openalex.org/W2397947827","https://openalex.org/W2402146185","https://openalex.org/W2460742184","https://openalex.org/W2515753980","https://openalex.org/W2515863432","https://openalex.org/W2533523411","https://openalex.org/W2558649592","https://openalex.org/W2587717635","https://openalex.org/W2604869594","https://openalex.org/W2616139854","https://openalex.org/W2962715207","https://openalex.org/W4245655784"],"related_works":["https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W163738850","https://openalex.org/W4379623495","https://openalex.org/W3094101084","https://openalex.org/W3111677651","https://openalex.org/W2533072256","https://openalex.org/W2279513239","https://openalex.org/W2294451595","https://openalex.org/W2025991752"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,40],"propose":[4],"a":[5],"novel":[6],"technique":[7,26],"for":[8,34,54,68],"direct":[9],"recognition":[10,37],"of":[11,19,75],"multiple":[12],"speech":[13,36],"streams":[14],"given":[15],"the":[16,42,51,60,63,73,76,83,90,109],"single":[17],"channel":[18],"mixed":[20,104],"speech,":[21],"without":[22],"first":[23],"separating":[24],"them.Our":[25],"is":[27,112],"based":[28],"on":[29,102],"permutation":[30,92],"invariant":[31],"training":[32],"(PIT)":[33],"automatic":[35],"(ASR).In":[38],"PIT-ASR,":[39],"compute":[41],"average":[43],"cross":[44],"entropy":[45],"(CE)":[46],"over":[47],"all":[48,72],"frames":[49,74],"in":[50,98],"whole":[52],"utterance":[53],"each":[55],"possible":[56],"output-target":[57],"assignment,":[58],"pick":[59],"one":[61,99],"with":[62,82],"minimum":[64],"CE,":[65],"and":[66,94],"optimize":[67],"that":[69,108],"assignment.PIT-ASR":[70],"forces":[71],"same":[77,84],"speaker":[78,95],"to":[79],"be":[80],"aligned":[81],"output":[85],"layer.This":[86],"strategy":[87],"elegantly":[88],"solves":[89],"label":[91],"problem":[93,97],"tracing":[96],"shot.Our":[100],"experiments":[101],"artificially":[103],"AMI":[105],"data":[106],"showed":[107],"proposed":[110],"approach":[111],"very":[113],"promising.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}