{"id":"https://openalex.org/W3011475224","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023163","title":"Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation","display_name":"Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011475224","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023163","mag":"3011475224"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101623835","display_name":"Lu Huang","orcid":"https://orcid.org/0000-0002-1588-8669"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Huang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072887461","display_name":"Gaofeng Cheng","orcid":"https://orcid.org/0000-0002-2102-6061"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Cheng","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021691632","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0008-3354-9207"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049134051","display_name":"Shumin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152501","display_name":"China Power Engineering Consulting Group (China)","ror":"https://ror.org/04t59qd02","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210152501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shumin Xu","raw_affiliation_strings":["North China Power Engineering CO., LTD. of China Power Engineering Consulting Group"],"affiliations":[{"raw_affiliation_string":"North China Power Engineering CO., LTD. of China Power Engineering Consulting Group","institution_ids":["https://openalex.org/I4210152501"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100298903","display_name":"Jiasong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiasong Sun","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101623835"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3317,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59439057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"1256","last_page":"1261"},"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":0.9968000054359436,"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":0.7648094892501831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6670942902565002},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6569170951843262},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5410609841346741},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5077301263809204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3100917935371399},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.059774309396743774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648094892501831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6670942902565002},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6569170951843262},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5410609841346741},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5077301263809204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100917935371399},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.059774309396743774}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1665214252","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2127851351","https://openalex.org/W2136848157","https://openalex.org/W2143169494","https://openalex.org/W2143612262","https://openalex.org/W2221409856","https://openalex.org/W2329068866","https://openalex.org/W2460742184","https://openalex.org/W2533523411","https://openalex.org/W2558649592","https://openalex.org/W2631415506","https://openalex.org/W2729190387","https://openalex.org/W2734774145","https://openalex.org/W2738829388","https://openalex.org/W2800022361","https://openalex.org/W2888957211","https://openalex.org/W2889010580","https://openalex.org/W2889129873","https://openalex.org/W2889540509","https://openalex.org/W2890505457","https://openalex.org/W2892025684","https://openalex.org/W2916979304","https://openalex.org/W2919115771","https://openalex.org/W2953384591","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W2964084166","https://openalex.org/W3099832538","https://openalex.org/W6607486085","https://openalex.org/W6637242042","https://openalex.org/W6713134421","https://openalex.org/W6728841359"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Utterance-level":[0],"permutation":[1],"invariant":[2],"training":[3,73],"(uPIT)":[4],"has":[5,37,45],"achieved":[6],"promising":[7],"progress":[8],"on":[9,119],"single-channel":[10],"multi-talker":[11],"speech":[12,67],"separation":[13,28,77,114,124],"task.":[14],"Long":[15],"short-term":[16],"memory":[17],"(LSTM)":[18],"and":[19,34,65,82,135],"bidirectional":[20],"LSTM":[21],"(BLSTM)":[22],"are":[23,84],"widely":[24],"used":[25,97],"as":[26],"the":[27,105,113,120,126],"networks":[29],"of":[30,116,129],"uPIT,":[31],"i.e.":[32],"uPIT-LSTM":[33,36],"uPIT-BLSTM.":[35],"lower":[38],"latency":[39],"but":[40,48],"worse":[41],"performance,":[42],"while":[43],"uPIT-BLSTM":[44,134],"better":[46,72],"performance":[47,115],"higher":[49],"latency.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"using":[56],"latency-controlled":[57],"BLSTM":[58],"(LC-BLSTM)":[59],"during":[60,98],"inference":[61],"to":[62,139],"fulfill":[63],"low-latency":[64],"good-performance":[66],"separation.":[68],"To":[69],"find":[70],"a":[71],"strategy":[74],"for":[75],"BLSTM-based":[76],"network,":[78],"chunk-level":[79],"PIT":[80],"(cPIT)":[81],"uPIT":[83,91],"compared.":[85],"The":[86],"experimental":[87],"results":[88],"show":[89],"that":[90,104],"outperforms":[92],"cPIT":[93],"when":[94],"LC-BLSTM":[95],"is":[96,101,137],"inference.":[99],"It":[100],"also":[102],"found":[103],"inter-chunk":[106],"speaker":[107],"tracing":[108],"(ST)":[109],"can":[110],"further":[111],"improve":[112],"uPIT-LC-BLSTM.":[117],"Evaluated":[118],"WSJO":[121],"two-talker":[122],"mixed-speech":[123],"task,":[125],"absolute":[127],"gap":[128],"signal-to-distortion":[130],"ratio":[131],"(SDR)":[132],"between":[133],"uPIT-LC-BLSTM":[136],"reduced":[138],"within":[140],"0.7":[141],"dB.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}