{"id":"https://openalex.org/W4406261035","doi":"https://doi.org/10.1109/bibm62325.2024.10822278","title":"Adaptive Data Augmentation with NaturalSpeech3 for Far-field Speaker Verification","display_name":"Adaptive Data Augmentation with NaturalSpeech3 for Far-field Speaker Verification","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406261035","doi":"https://doi.org/10.1109/bibm62325.2024.10822278"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5100425719","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0003-1641-7831"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074318258","display_name":"Jiyao Liu","orcid":"https://orcid.org/0000-0002-3316-5704"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyao Liu","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100425719"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23295298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5662","last_page":"5669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9902999997138977,"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":0.9902999997138977,"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":0.9742000102996826,"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":0.82016921043396},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.8185346126556396},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48542866110801697},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4409177601337433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43225133419036865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82016921043396},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8185346126556396},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48542866110801697},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4409177601337433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43225133419036865},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/bibm62325.2024.10822278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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":37,"referenced_works":["https://openalex.org/W2058751961","https://openalex.org/W2696967604","https://openalex.org/W2784941364","https://openalex.org/W2890964092","https://openalex.org/W2891803057","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2969985801","https://openalex.org/W2972315886","https://openalex.org/W2972668418","https://openalex.org/W2972697221","https://openalex.org/W2973190269","https://openalex.org/W2978904488","https://openalex.org/W2981087920","https://openalex.org/W3012367631","https://openalex.org/W3015503328","https://openalex.org/W3024869864","https://openalex.org/W3026870722","https://openalex.org/W3049278490","https://openalex.org/W3094872920","https://openalex.org/W3095123370","https://openalex.org/W3096066489","https://openalex.org/W3097224504","https://openalex.org/W3161294170","https://openalex.org/W3203468141","https://openalex.org/W3212414183","https://openalex.org/W4205143758","https://openalex.org/W4224917914","https://openalex.org/W4225276605","https://openalex.org/W4296068430","https://openalex.org/W4297841892","https://openalex.org/W4372260283","https://openalex.org/W4372342894","https://openalex.org/W4372348291","https://openalex.org/W6688816777","https://openalex.org/W6754473786","https://openalex.org/W6862144568"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"The":[0],"scarcity":[1],"of":[2,48,126,158,196,229],"speaker-annotated":[3],"far-field":[4,13,42,49,75,79,127,141,161,177,232],"speech":[5,24,43,59,73,76,95,111,128,136,142,152,190],"presents":[6],"a":[7,27,64],"significant":[8],"challenge":[9],"in":[10,36,191,209],"developing":[11],"high-performance":[12],"speaker":[14,132,146,178],"verification":[15,179],"(SV)":[16],"systems.":[17],"While":[18],"data":[19,84,175,221,248,267],"augmentation":[20,60,185,195,222,238,249,268],"using":[21],"large-scale":[22],"near-field":[23,40,72,135,151],"has":[25],"been":[26],"common":[28],"strategy":[29,171],"to":[30,70,92,137,183],"address":[31],"this":[32,53],"limitation,":[33],"the":[34,46,94,110,120,145,149,155,159,201,226,230,246],"mismatch":[35],"acoustic":[37,80,156,227],"environments":[38],"between":[39,215],"and":[41,104,123,188,198,217,260],"significantly":[44,251],"hinders":[45],"improvement":[47],"SV":[50],"effectiveness.":[51],"In":[52,117,194],"paper,":[54],"we":[55,87],"propose":[56],"an":[57,169,236],"adaptive":[58,237,247],"approach":[61,164],"leveraging":[62],"NaturalSpeech3,":[63],"pre-trained":[65],"foundation":[66],"text-to-speech":[67],"(TTS)":[68],"model,":[69],"convert":[71],"into":[74,97],"by":[77,207],"incorporating":[78],"ambient":[81],"noise":[82,214,258],"for":[83,172,176,186],"augmentation.":[85],"Specifically,":[86],"utilize":[88],"FACodec":[89],"from":[90,113,134,148],"NaturalSpeech3":[91],"decompose":[93],"waveform":[96,112],"distinct":[98],"embedding":[99],"subspaces":[100],"\u2014content,":[101],"prosody,":[102,121],"speaker,":[103],"residual":[105,124],"(acoustic":[106],"details)":[107],"embeddings\u2014and":[108],"reconstruct":[109],"these":[114],"disentangled":[115],"representations.":[116],"our":[118],"method,":[119,223],"content,":[122],"embeddings":[125,133],"are":[129],"combined":[130],"with":[131],"generate":[138],"augmented":[139],"pseudo":[140],"that":[143,245],"maintains":[144],"identity":[147],"out-domain":[150],"while":[153],"preserving":[154],"environment":[157,228],"in-domain":[160,231],"speech.":[162],"This":[163,220],"not":[165],"only":[166],"serves":[167],"as":[168,235,256,262,264],"effective":[170],"augmenting":[173],"training":[174],"but":[180],"also":[181],"extends":[182],"cross-data":[184],"enrollment":[187,197,216],"test":[189,199,218],"evaluation":[192],"trials.":[193],"utterances,":[200],"method":[202,250],"mitigates":[203],"performance":[204],"degradation":[205],"caused":[206],"discrepancies":[208],"text":[210],"content":[211],"or":[212],"environmental":[213],"data.":[219],"which":[224],"preserves":[225],"data,":[233],"qualifies":[234],"method.":[239],"Experimental":[240],"results":[241],"on":[242],"FFSVC":[243],"demonstrate":[244],"outperforms":[252],"traditional":[253],"approaches,":[254],"such":[255],"random":[257],"addition":[259],"reverberation,":[261],"well":[263],"other":[265],"competitive":[266],"strategies.":[269]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
