{"id":"https://openalex.org/W2937813194","doi":"https://doi.org/10.1109/icassp.2019.8683762","title":"A Robust Text-independent Speaker Verification Method Based on Speech Separation and Deep Speaker","display_name":"A Robust Text-independent Speaker Verification Method Based on Speech Separation and Deep Speaker","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937813194","doi":"https://doi.org/10.1109/icassp.2019.8683762","mag":"2937813194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683762","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/A5090607458","display_name":"Fei Zhao","orcid":"https://orcid.org/0000-0002-8198-3787"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Zhao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348614","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-5963-4505"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090607458"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":2.9854,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91935682,"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":"6101","last_page":"6105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.8362391591072083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126574754714966},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7971403002738953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7833024263381958},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7064446210861206},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5154045820236206},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.513440728187561},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4843772351741791},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46862509846687317},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46832922101020813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4663746953010559},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4603123664855957},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44887781143188477},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4476442337036133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4355453550815582},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42827194929122925},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21597376465797424}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8362391591072083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126574754714966},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7971403002738953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7833024263381958},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7064446210861206},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5154045820236206},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.513440728187561},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4843772351741791},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46862509846687317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46832922101020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4663746953010559},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4603123664855957},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44887781143188477},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4476442337036133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4355453550815582},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42827194929122925},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21597376465797424},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683762","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":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1499332833","https://openalex.org/W1522301498","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2292259253","https://openalex.org/W2599685671","https://openalex.org/W2612434969","https://openalex.org/W2678916739","https://openalex.org/W2718701456","https://openalex.org/W2748488820","https://openalex.org/W2889442120","https://openalex.org/W2890964092","https://openalex.org/W2892129657","https://openalex.org/W2899771611","https://openalex.org/W2962751625","https://openalex.org/W2962866211","https://openalex.org/W2962959915","https://openalex.org/W2963403664","https://openalex.org/W2964121744","https://openalex.org/W3099206234","https://openalex.org/W6631190155","https://openalex.org/W6691430256","https://openalex.org/W6737575990","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Recently,":[0],"deep":[1,97],"neural":[2],"networks":[3],"(DNNs)":[4],"have":[5],"achieved":[6],"incredible":[7],"performance":[8,112],"in":[9,113],"speaker":[10,28,83,90,98],"verification.":[11],"However,":[12],"most":[13],"of":[14,54,58,76],"which":[15],"remains":[16],"sensitive":[17],"to":[18,31,47,81],"environment":[19],"noise.":[20,37],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"an":[26],"end-to-end":[27],"verification":[29,84,91],"framework":[30,40],"enhance":[32],"the":[33,52,55,59,64,70,82,105],"robustness":[34],"against":[35],"background":[36],"The":[38,86],"proposed":[39,106],"first":[41],"utilizes":[42],"convolutional":[43],"recurrent":[44],"network":[45],"(CRN)":[46],"address":[48],"speech":[49,78,87],"separation.":[50],"Then":[51],"output":[53],"middle":[56],"layer":[57],"CRN":[60],"is":[61],"used":[62],"as":[63],"auxiliary":[65],"feature,":[66],"and":[67,89,99],"together":[68],"with":[69,96],"robust":[71],"Filter":[72],"banks":[73],"(Fbanks)":[74],"feature":[75],"noisy":[77,114],"are":[79,92],"fed":[80],"system.":[85],"separation":[88],"jointly":[93],"optimized.":[94],"Compared":[95],"DNN/i-vector,":[100],"systematic":[101],"evaluation":[102],"indicates":[103],"that":[104],"algorithm":[107],"can":[108],"obtain":[109],"a":[110],"better":[111],"conditions.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}