{"id":"https://openalex.org/W2802905931","doi":"https://doi.org/10.1109/icassp.2018.8462311","title":"A Novel LSTM-Based Speech Preprocessor for Speaker Diarization in Realistic Mismatch Conditions","display_name":"A Novel LSTM-Based Speech Preprocessor for Speaker Diarization in Realistic Mismatch Conditions","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802905931","doi":"https://doi.org/10.1109/icassp.2018.8462311","mag":"2802905931"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590046","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0002-9523-5560"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062616905","display_name":"Yu-Ding Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ding Lu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088320958","display_name":"Neville Ryant","orcid":"https://orcid.org/0000-0003-2545-6912"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neville Ryant","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I4210120198","https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4917,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93645311,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5234","last_page":"5238"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/preprocessor","display_name":"Preprocessor","score":0.8506697416305542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8141762018203735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7367508411407471},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7056089043617249},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.654738187789917},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5658308863639832},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5301010608673096},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49355804920196533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46651020646095276},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46532246470451355},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4227445721626282},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4115789532661438},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12152233719825745}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8506697416305542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141762018203735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7367508411407471},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7056089043617249},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.654738187789917},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5658308863639832},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5301010608673096},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49355804920196533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46651020646095276},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46532246470451355},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4227445721626282},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4115789532661438},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12152233719825745},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1561065572","https://openalex.org/W1608667326","https://openalex.org/W1815076433","https://openalex.org/W2035576074","https://openalex.org/W2069642050","https://openalex.org/W2078528584","https://openalex.org/W2081074144","https://openalex.org/W2083751884","https://openalex.org/W2098726438","https://openalex.org/W2114970513","https://openalex.org/W2116261113","https://openalex.org/W2119968850","https://openalex.org/W2121973264","https://openalex.org/W2132990350","https://openalex.org/W2136848157","https://openalex.org/W2141411743","https://openalex.org/W2153894152","https://openalex.org/W2168379380","https://openalex.org/W2170695863","https://openalex.org/W2338994564","https://openalex.org/W2405774341","https://openalex.org/W2510280606","https://openalex.org/W2516547830","https://openalex.org/W2605589342","https://openalex.org/W2612688029","https://openalex.org/W2891433113","https://openalex.org/W2963446712","https://openalex.org/W3147539069","https://openalex.org/W4255455116","https://openalex.org/W6603616073","https://openalex.org/W6605762983","https://openalex.org/W6638545294","https://openalex.org/W6679595104","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0],"this":[1,89],"study,":[2],"we":[3],"investigate":[4],"on":[5,122],"the":[6,26,35,38,46,69,101,112,117,131,136,153],"effects":[7],"of":[8,49,111,147],"deep":[9,70],"learning":[10,56,62],"based":[11],"speech":[12,81,104,139,158],"enhancement":[13,161],"as":[14],"a":[15,93],"preprocessor":[16,91,140],"to":[17,97],"speaker":[18,98],"diarization":[19,133,148],"in":[20,105,109],"quite":[21],"challenging":[22,124],"realistic":[23,102],"environments":[24],"involving":[25],"background":[27],"noises,":[28],"reverberations":[29],"and":[30,57,82,116,129,144,159],"overlapping":[31],"speech.":[32],"To":[33],"improve":[34],"generalization":[36,95],"capability,":[37],"advanced":[39],"long":[40],"short-term":[41],"memory":[42],"(LSTM)":[43],"architecture":[44],"with":[45,100,135],"novel":[47,137],"design":[48],"hidden":[50],"layers":[51],"via":[52,60],"densely":[53],"connected":[54],"progressive":[55],"output":[58],"layer":[59],"multiple-target":[61],"is":[63],"proposed":[64,90],"for":[65],"preprocessing.":[66],"We":[67],"build":[68],"model":[71],"using":[72,155],"synthesized":[73],"training":[74],"data":[75],"pairs":[76],"generated":[77],"from":[78],"WSJO":[79],"reading-style":[80],"more":[83],"than":[84],"100":[85],"noise":[86],"types.":[87],"Surprisingly,":[88],"demonstrates":[92],"strong":[94],"capability":[96],"di-arization":[99],"noisy":[103,157],"highly":[106],"mismatched":[107],"conditions,":[108],"terms":[110],"speaking":[113],"style,":[114],"interferences,":[115],"interaction":[118],"between":[119],"them.":[120],"Tested":[121],"three":[123],"tasks,":[125],"namely":[126],"AMI,":[127],"ADOS,":[128],"SeedLings,":[130],"state-of-the-art":[132],"system":[134],"LSTM-based":[138],"can":[141],"yield":[142],"consistent":[143],"significant":[145],"reductions":[146],"error":[149],"rate":[150],"(DER)":[151],"over":[152],"systems":[154],"unprocessed":[156],"traditional":[160],"methods.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}