{"id":"https://openalex.org/W3012484546","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023256","title":"Alleviate Cross-chunk Permutation through Chunk-level Speaker Embedding for Blind Speech Separation","display_name":"Alleviate Cross-chunk Permutation through Chunk-level Speaker Embedding for Blind Speech Separation","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012484546","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023256","mag":"3012484546"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023256","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/A5038895203","display_name":"Rongzhi Gu","orcid":"https://orcid.org/0000-0003-1861-9170"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongzhi Gu","raw_affiliation_strings":["ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111291634","display_name":"Junyi Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Peng","raw_affiliation_strings":["ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"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/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":"Dong Yu","raw_affiliation_strings":["Tencent AI LAB"],"affiliations":[{"raw_affiliation_string":"Tencent AI LAB","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038895203"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20093286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":null,"first_page":"325","last_page":"331"},"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7636134624481201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7029579877853394},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6814154386520386},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6648204326629639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6590465307235718},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6440436840057373},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6012597680091858},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4637952446937561},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4363086521625519},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4275050163269043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4194277822971344},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4119222164154053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3907507658004761}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7636134624481201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7029579877853394},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6814154386520386},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6648204326629639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6590465307235718},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6440436840057373},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6012597680091858},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4637952446937561},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4363086521625519},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4275050163269043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194277822971344},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4119222164154053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3907507658004761},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023256","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":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1896424170","https://openalex.org/W1991139021","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2296073425","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2749660340","https://openalex.org/W2782360754","https://openalex.org/W2800022361","https://openalex.org/W2801839390","https://openalex.org/W2891405874","https://openalex.org/W2892163332","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2964238697","https://openalex.org/W2972460025","https://openalex.org/W3021863355","https://openalex.org/W6631190155","https://openalex.org/W6639495226","https://openalex.org/W6719599463","https://openalex.org/W6743590492","https://openalex.org/W6747088889"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Speaker-independent":[0],"speech":[1,7,24,102,178],"separation":[2,25],"(SI-SS)":[3],"refers":[4],"to":[5,58,61,83,110,136,141,149,164,187,222],"recovering":[6],"of":[8,146],"unknown":[9,85],"speakers":[10],"from":[11,52,87],"multispeaker":[12],"mixtures.":[13],"The":[14,192],"well-known":[15,198],"deep":[16,139],"clustering":[17,29],"(DC)":[18],"based":[19],"SI-SS":[20],"methods":[21,227],"cast":[22],"the":[23,49,53,70,88,92,94,128,132,143,159,166,177,181,189,197,201],"problem":[26,30,125],"into":[27,75],"a":[28,111,138,175],"in":[31,156,228],"an":[32,84],"embedding":[33,153],"space,":[34],"where":[35,79],"time-frequency":[36],"(T-F)":[37],"features":[38],"are":[39,56,73,97,162,185],"encoded":[40],"as":[41,131],"high-dimensional":[42],"vectors":[43],"(T-F":[44],"embeddings).":[45],"In":[46,67,116],"training":[47],"stage,":[48,69,158],"T-F":[50,71,95,144],"embeddings":[51,72,96,145],"same":[54],"speaker":[55,86,129,152],"trained":[57],"be":[59],"close":[60],"each":[62,80,169],"other,":[63],"otherwise":[64],"far":[65],"away.":[66],"prediction":[68,157],"partitioned":[74],"clusters":[76],"by":[77,126],"K-Means,":[78],"cluster":[81,148,170],"corresponds":[82],"mixture.":[89],"To":[90],"reduce":[91],"latency,":[93],"usually":[98],"extracted":[99],"on":[100,121,196],"short":[101],"chunks":[103,179],"rather":[104],"than":[105],"utterances,":[106],"which":[107],"unfortunately":[108],"leads":[109],"cross-chunk":[112],"permutation":[113],"(CCP)":[114],"problem.":[115],"this":[117,123],"study,":[118],"we":[119,212],"focus":[120],"solving":[122],"CCP":[124],"using":[127],"labels":[130],"auxiliary":[133],"supervision":[134],"information":[135],"train":[137],"model":[140],"map":[142],"one":[147,150],"chunk-level":[151],"(CL-SE).":[154],"Therefore,":[155],"generated":[160],"CL-SEs":[161,184],"used":[163],"calculate":[165],"similarity":[167],"between":[168],"over":[171,217,224],"consecutive":[172],"chunks.":[173],"As":[174],"result,":[176],"with":[180],"more":[182],"similar":[183],"concatenated":[186],"yield":[188],"complete":[190],"utterances.":[191],"evaluation":[193],"is":[194,205],"conducted":[195],"WSJ0-2mix":[199],"and":[200,220],"signal-to-distortion":[202],"ratio":[203],"(SDR)":[204],"adopted":[206],"for":[207],"performance":[208],"evaluation.":[209],"Noted":[210],"that":[211],"obtain":[213],"41%":[214],"SDR":[215],"gain":[216],"DC":[218],"baseline":[219],"up":[221],"32%":[223],"other":[225],"speaker-aware":[226],"open":[229],"conditions.":[230]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}