{"id":"https://openalex.org/W2936794852","doi":"https://doi.org/10.1109/icassp.2019.8683612","title":"Pre-training of Speaker Embeddings for Low-latency Speaker Change Detection in Broadcast News","display_name":"Pre-training of Speaker Embeddings for Low-latency Speaker Change Detection in Broadcast News","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936794852","doi":"https://doi.org/10.1109/icassp.2019.8683612","mag":"2936794852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5003052411","display_name":"Leda Sar\u0131","orcid":"https://orcid.org/0000-0002-3754-1156"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Leda Sari","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003052411"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.6802,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88081728,"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":"6286","last_page":"6290"},"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":0.9984999895095825,"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":0.993399977684021,"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":0.8101402521133423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6715105772018433},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.602656364440918},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5989292860031128},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5698610544204712},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.48369652032852173},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47840842604637146},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4719373881816864},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47044557332992554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4484637677669525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41672688722610474},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4111872911453247},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08645063638687134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101402521133423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6715105772018433},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.602656364440918},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5989292860031128},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5698610544204712},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.48369652032852173},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47840842604637146},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4719373881816864},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47044557332992554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4484637677669525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41672688722610474},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4111872911453247},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08645063638687134}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.5799999833106995,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W21371201","https://openalex.org/W67277430","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1585610988","https://openalex.org/W2010114458","https://openalex.org/W2064675550","https://openalex.org/W2150769028","https://openalex.org/W2166980079","https://openalex.org/W2402704384","https://openalex.org/W2516890051","https://openalex.org/W2618760106","https://openalex.org/W2673722796","https://openalex.org/W2746241180","https://openalex.org/W2746574320","https://openalex.org/W2748488820","https://openalex.org/W2888776417","https://openalex.org/W2963702081","https://openalex.org/W6600930061","https://openalex.org/W6602762607","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6635035540","https://openalex.org/W6713082170"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"In":[0,110,141,172],"this":[1],"work,":[2],"we":[3,95],"investigate":[4,47],"pre-training":[5,56,157],"of":[6,57,65,88],"neural":[7],"network":[8,182],"based":[9,55,82,124,148,156,183],"speaker":[10,14,80,86],"embeddings":[11,25,35,184],"for":[12,105,181],"low-latency":[13,103],"change":[15],"detection.":[16],"Our":[17],"proposed":[18,153],"system":[19,99],"takes":[20],"two":[21],"speech":[22,121],"segments,":[23],"generates":[24],"using":[26,188],"shared":[27],"Siamese":[28],"layers":[29,60,68],"and":[30,52,61,169],"then":[31],"classifies":[32],"the":[33,43,58,66,97,145,152,174,191],"concatenated":[34],"depending":[36],"on":[37,77,83],"whether":[38],"they":[39],"are":[40,116,130],"spoken":[41],"by":[42,159],"same":[44],"speaker.":[45],"We":[46],"gender":[48],"classification,":[49],"contrastive":[50],"loss":[51,54,155],"triplet":[53,154],"embedding":[59,67],"also":[62],"joint":[63,160],"training":[64,161],"along":[69],"with":[70],"a":[71,101],"same/different":[72],"classifier.":[73],"Training":[74],"is":[75,178],"performed":[76],"2-second":[78],"single":[79],"segments":[81,129],"ground":[84],"truth":[85],"segmentation":[87,125],"broadcast":[89],"news":[90],"data.":[91],"However,":[92],"during":[93,139],"test,":[94],"use":[96],"detection":[98],"in":[100,167,176,190],"practical":[102],"setting":[104],"annotating":[106],"automatic":[107,120],"closed":[108],"captions.":[109],"contrast":[111],"to":[112,187],"training,":[113],"test":[114,194],"pairs":[115],"now":[117],"created":[118],"around":[119],"recognition":[122],"(ASR)":[123],"boundaries.":[126],"The":[127],"ASR":[128],"often":[131],"shorter":[132],"than":[133],"2":[134],"seconds":[135],"causing":[136],"duration":[137,193],"mismatch":[138],"testing.":[140],"our":[142],"experiments,":[143],"although":[144],"baseline":[146],"i-vector":[147],"classifier":[149],"performs":[150],"well,":[151],"followed":[158],"provides":[162],"7-50%":[163],"relative":[164],"F-measure":[165],"improvement":[166],"matched":[168],"mismatched":[170],"conditions.":[171,195],"addition,":[173],"degradation":[175],"performance":[177],"less":[179],"severe":[180],"as":[185],"compared":[186],"i-vectors":[189],"variable":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}