{"id":"https://openalex.org/W4327521002","doi":"https://doi.org/10.1145/3573428.3573649","title":"Data augmentation for speaker verification","display_name":"Data augmentation for speaker verification","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4327521002","doi":"https://doi.org/10.1145/3573428.3573649"},"language":"en","primary_location":{"id":"doi:10.1145/3573428.3573649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052653345","display_name":"Shiqing Yang","orcid":"https://orcid.org/0000-0002-7639-6174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqing Yang","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-7639-6174","affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033172951","display_name":"Min Liu","orcid":"https://orcid.org/0000-0003-4792-4051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Liu","raw_affiliation_strings":["SpeakIn Technologies Co. Ltd., China"],"raw_orcid":"https://orcid.org/0000-0003-4792-4051","affiliations":[{"raw_affiliation_string":"SpeakIn Technologies Co. Ltd., China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1247","last_page":"1251"},"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.8084266185760498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6663051247596741},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5882466435432434},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5744152665138245},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48254936933517456},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46552154421806335},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44177156686782837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41661423444747925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3779650330543518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084266185760498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6663051247596741},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5882466435432434},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5744152665138245},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48254936933517456},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46552154421806335},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44177156686782837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41661423444747925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3779650330543518},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573428.3573649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","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":23,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2130942839","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2278339107","https://openalex.org/W2746314669","https://openalex.org/W2747165665","https://openalex.org/W2775304348","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2963420686","https://openalex.org/W3008625353","https://openalex.org/W3015368919","https://openalex.org/W3034303554","https://openalex.org/W3103152812","https://openalex.org/W4385245566","https://openalex.org/W6679436768","https://openalex.org/W6739901393","https://openalex.org/W6743731764","https://openalex.org/W6761843422"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,16,25,42,48],"is":[2,38,43],"a":[3,44,85],"hot":[4],"issue":[5],"in":[6,125],"neural":[7,32],"network":[8,33],"training.":[9],"In":[10],"this":[11],"paper,":[12],"we":[13,21,111],"investigate":[14,74],"data":[15,24,47],"for":[17],"speaker":[18],"recognition,":[19],"and":[20,55,117,128],"propose":[22],"two":[23,99],"methods":[26,100],"to":[27,52],"enhance":[28],"the":[29,75,82,103,122,126],"performance":[30],"of":[31,36,62,69,77,84],"system.":[34],"One":[35],"which":[37,50,80],"spectral":[39],"augmentation.":[40],"Spectral":[41],"newly":[45],"proposed":[46],"method":[49,76],"applied":[51],"speech":[53],"recognition":[54],"got":[56],"state-of-the-art":[57],"performance,":[58],"by":[59,66],"masking":[60,67],"blocks":[61,68],"frequency":[63],"channels(F-mask),":[64],"and/or":[65],"time":[70],"steps(T-mask).":[71],"We":[72],"also":[73],"speed":[78,109],"perturbation,":[79,110],"adjusts":[81],"time-scale":[83],"given":[86],"audio":[87],"signal":[88],"without":[89],"altering":[90],"its":[91],"pitch":[92],"content.":[93],"Experimental":[94],"results":[95],"show":[96],"that":[97],"both":[98],"can":[101,112],"boost":[102],"performance.":[104],"By":[105],"combining":[106],"TF-mask":[107],"with":[108],"obtain":[113],"more":[114],"than":[115],"5.2%":[116],"8.7%":[118],"relative":[119],"improvements":[120],"over":[121],"baseline":[123],"systems":[124],"Vox-H":[127],"WX":[129],"tasks.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
