{"id":"https://openalex.org/W3015611708","doi":"https://doi.org/10.1109/icassp40776.2020.9053481","title":"Investigation of Specaugment for Deep Speaker Embedding Learning","display_name":"Investigation of Specaugment for Deep Speaker Embedding Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015611708","doi":"https://doi.org/10.1109/icassp40776.2020.9053481","mag":"3015611708"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239262","display_name":"Johan Rohdin","orcid":"https://orcid.org/0000-0003-0978-2064"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Johan Rohdin","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Oldrich Plchot","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100328272"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.6998,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.94218677,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7139","last_page":"7143"},"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":0.9990000128746033,"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":0.9988999962806702,"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/nist","display_name":"NIST","score":0.8792047500610352},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8500784635543823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7869313955307007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.714933454990387},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5797699093818665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5789445638656616},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.542446494102478},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5079091191291809},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48337143659591675},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4634976089000702},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4575658440589905}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8792047500610352},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8500784635543823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869313955307007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.714933454990387},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5797699093818665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789445638656616},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.542446494102478},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5079091191291809},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48337143659591675},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4634976089000702},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4575658440589905}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1999033484","https://openalex.org/W2046056978","https://openalex.org/W2095705004","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2584329820","https://openalex.org/W2587150483","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2747685395","https://openalex.org/W2784163702","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2891138528","https://openalex.org/W2936774411","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2998508940","https://openalex.org/W3010925296","https://openalex.org/W3103152812","https://openalex.org/W6674330103","https://openalex.org/W6684191040","https://openalex.org/W6743440100"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4306178031","https://openalex.org/W2118039276","https://openalex.org/W4381430104","https://openalex.org/W2786391746","https://openalex.org/W3132346564","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W2995102745","https://openalex.org/W1990237101"],"abstract_inverted_index":{"SpecAugment":[0,35,78],"is":[1],"a":[2],"newly":[3],"proposed":[4],"data":[5,83,91],"augmentation":[6,92],"method":[7,21],"for":[8,36,100],"speech":[9],"recognition.":[10],"By":[11,76],"randomly":[12],"masking":[13],"bands":[14],"in":[15,84],"the":[16,32,69,80],"log":[17],"Mel":[18],"spectogram":[19],"this":[20,28],"leads":[22],"to":[23,60,79],"impressive":[24],"performance":[25],"improvements.":[26],"In":[27],"paper,":[29],"we":[30,94,112],"investigate":[31],"usage":[33],"of":[34],"speaker":[37],"verification":[38],"tasks.":[39],"Two":[40],"different":[41],"models,":[42],"namely":[43],"1-D":[44],"convolutional":[45,49],"TDNN":[46],"and":[47,71,97,105],"2-D":[48],"ResNet34,":[50],"trained":[51],"with":[52],"either":[53],"Softmax":[54],"or":[55],"AAM-Softmax":[56],"loss,":[57],"are":[58,65],"used":[59],"analyze":[61],"SpecAugment's":[62],"effectiveness.":[63],"Experiments":[64],"carried":[66],"out":[67],"on":[68],"Voxceleb":[70],"NIST":[72,101],"SRE":[73,102],"2016":[74,103],"dataset.":[75],"applying":[77],"original":[81],"clean":[82],"an":[85],"on-the-fly":[86],"manner":[87],"without":[88],"complex":[89],"off-line":[90],"methods,":[93],"obtained":[95,113],"3.72%":[96],"11.49%":[98],"EER":[99],"Cantonese":[104],"Tagalog,":[106],"respectively.":[107],"For":[108],"Voxceleb1":[109],"evaluation":[110],"set,":[111],"1.47%":[114],"EER.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}