{"id":"https://openalex.org/W2658996865","doi":"https://doi.org/10.1109/icassp.2017.7953088","title":"Training algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis","display_name":"Training algorithm to deceive Anti-Spoofing Verification for DNN-based speech synthesis","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2658996865","doi":"https://doi.org/10.1109/icassp.2017.7953088","mag":"2658996865"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4900","last_page":"4904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9904000163078308,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7846696972846985},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7135540246963501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5838469862937927},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.514037013053894},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49858975410461426},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42924830317497253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38473042845726013},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.329546183347702},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2261916995048523},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14700445532798767}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846696972846985},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7135540246963501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5838469862937927},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.514037013053894},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49858975410461426},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42924830317497253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38473042845726013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.329546183347702},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2261916995048523},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14700445532798767},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/10","score":0.6000000238418579,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1517202054","https://openalex.org/W1523372075","https://openalex.org/W1576227399","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2099471712","https://openalex.org/W2100495367","https://openalex.org/W2102003408","https://openalex.org/W2111194146","https://openalex.org/W2111284386","https://openalex.org/W2120605154","https://openalex.org/W2129142580","https://openalex.org/W2146502635","https://openalex.org/W2156387975","https://openalex.org/W2165700458","https://openalex.org/W2274854232","https://openalex.org/W2282821441","https://openalex.org/W2293049663","https://openalex.org/W2294013337","https://openalex.org/W2395578248","https://openalex.org/W2396990910","https://openalex.org/W2401839215","https://openalex.org/W2403471241","https://openalex.org/W2404100688","https://openalex.org/W2405756170","https://openalex.org/W2407039802","https://openalex.org/W2473388484","https://openalex.org/W2517788403","https://openalex.org/W3123963976","https://openalex.org/W4320013936","https://openalex.org/W4395958265","https://openalex.org/W6630905448","https://openalex.org/W6631309588","https://openalex.org/W6675380101","https://openalex.org/W6676358011","https://openalex.org/W6681435938","https://openalex.org/W6682889407","https://openalex.org/W6684185306","https://openalex.org/W6711777497","https://openalex.org/W6712112783","https://openalex.org/W6712941293","https://openalex.org/W6713400016","https://openalex.org/W6713645886","https://openalex.org/W6713652182","https://openalex.org/W6714093102","https://openalex.org/W6864847698"],"related_works":["https://openalex.org/W4294437891","https://openalex.org/W4226389478","https://openalex.org/W4297792928","https://openalex.org/W3113108043","https://openalex.org/W4221161333","https://openalex.org/W2061278248","https://openalex.org/W4298202768","https://openalex.org/W1914348842","https://openalex.org/W2168254078","https://openalex.org/W2914486900"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,55],"novel":[4],"training":[5,133],"algorithm":[6,35,103,129,134],"for":[7,67],"high-quality":[8],"Deep":[9],"Neural":[10],"Network":[11],"(DNN)-based":[12],"speech":[13,19,68,79,86,96,120,138],"synthesis.":[14],"The":[15,33,52,122],"parameters":[16,80,87],"of":[17,118,137],"synthetic":[18,31,62,78,85,119],"tend":[20],"to":[21,58],"be":[22],"over-smoothed,":[23],"and":[24,61,115,140],"this":[25],"causes":[26],"significant":[27],"quality":[28],"degradation":[29],"in":[30,47,90,135],"speech.":[32,63],"proposed":[34],"takes":[36],"into":[37],"account":[38],"an":[39,44],"Anti-Spoofing":[40],"Verification":[41],"(ASV)":[42],"as":[43,81,94],"additional":[45],"constraint":[46],"the":[48,74,77,84,91,102,107,112,116,128,131,146],"acoustic":[49,65],"model":[50],"training.":[51],"ASV":[53,75],"is":[54,143],"discriminator":[56],"trained":[57,71],"distinguish":[59],"natural":[60,82,95],"Since":[64],"models":[66],"synthesis":[69],"are":[70,88],"so":[72],"that":[73,101,126],"recognizes":[76],"speech,":[83],"distributed":[89],"same":[92],"manner":[93],"parameters.":[97,121],"Additionally,":[98],"we":[99],"find":[100],"compensates":[104],"not":[105],"only":[106],"parameter":[108],"distributions,":[109],"but":[110],"also":[111],"global":[113],"variance":[114],"correlations":[117],"experimental":[123],"results":[124],"demonstrate":[125],"1)":[127],"outperforms":[130],"conventional":[132],"terms":[136],"quality,":[139],"2)":[141],"it":[142],"robust":[144],"against":[145],"hyper-parameter":[147],"settings.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}