{"id":"https://openalex.org/W4392903649","doi":"https://doi.org/10.1109/icassp48485.2024.10446471","title":"Mdrt: Multi-Domain Synthetic Speech Localization","display_name":"Mdrt: Multi-Domain Synthetic Speech Localization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903649","doi":"https://doi.org/10.1109/icassp48485.2024.10446471"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5055125973","display_name":"Amit Kumar Singh Yadav","orcid":"https://orcid.org/0000-0001-6464-7688"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Kumar Singh Yadav","raw_affiliation_strings":["Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022400610","display_name":"Kratika Bhagtani","orcid":"https://orcid.org/0000-0001-7399-4876"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kratika Bhagtani","raw_affiliation_strings":["Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085323232","display_name":"Sriram Baireddy","orcid":"https://orcid.org/0000-0002-4386-0065"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Baireddy","raw_affiliation_strings":["Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051370303","display_name":"Paolo Bestagini","orcid":"https://orcid.org/0000-0003-0406-0222"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Bestagini","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milan,Italy","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005378965","display_name":"Stefano Tubaro","orcid":"https://orcid.org/0000-0002-1990-9869"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Tubaro","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milan,Italy","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":["Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1336,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88498457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11171","last_page":"11175"},"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":0.9987999796867371,"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":0.9950000047683716,"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/spectrogram","display_name":"Spectrogram","score":0.8756662607192993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7919555902481079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6921926736831665},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6129031181335449},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5887501239776611},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47217458486557007},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44995927810668945},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.445970356464386},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43993720412254333},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42082715034484863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4194677472114563},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3580244183540344},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07901251316070557},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07544445991516113}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8756662607192993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919555902481079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6921926736831665},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6129031181335449},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5887501239776611},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47217458486557007},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44995927810668945},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.445970356464386},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43993720412254333},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42082715034484863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4194677472114563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3580244183540344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07901251316070557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07544445991516113},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1579019551","display_name":null,"funder_award_id":"FA8750-20-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8140536623","display_name":null,"funder_award_id":"FA8750-20-2-1004","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1604034532","https://openalex.org/W2062826588","https://openalex.org/W2103869314","https://openalex.org/W2590129515","https://openalex.org/W2733416080","https://openalex.org/W2752782242","https://openalex.org/W2936802426","https://openalex.org/W2955054437","https://openalex.org/W2964135678","https://openalex.org/W2964243274","https://openalex.org/W2967606780","https://openalex.org/W3016021263","https://openalex.org/W3036601975","https://openalex.org/W3170179936","https://openalex.org/W3196774886","https://openalex.org/W3197457172","https://openalex.org/W3200876013","https://openalex.org/W3205475937","https://openalex.org/W3209059054","https://openalex.org/W3211424380","https://openalex.org/W4297841480","https://openalex.org/W4313306150","https://openalex.org/W4313679638","https://openalex.org/W4323896824","https://openalex.org/W4362684594","https://openalex.org/W4372260253","https://openalex.org/W4372269174","https://openalex.org/W4372341324","https://openalex.org/W4372347465","https://openalex.org/W4375869244","https://openalex.org/W4378506723","https://openalex.org/W4379539302","https://openalex.org/W4381187661","https://openalex.org/W4381198892","https://openalex.org/W4382491261","https://openalex.org/W4385822372","https://openalex.org/W4385823002","https://openalex.org/W4385823015","https://openalex.org/W4385999783","https://openalex.org/W6757817989","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6810510949","https://openalex.org/W6848735303","https://openalex.org/W6852755086","https://openalex.org/W6852859116","https://openalex.org/W6853696097","https://openalex.org/W6945259040"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W596245619"],"abstract_inverted_index":{"With":[0],"recent":[1],"advancements":[2],"in":[3,71],"generating":[4],"synthetic":[5,11,26,43,53,68,74,81,128,161,177],"speech,":[6],"tools":[7],"to":[8,65,126,136,153],"generate":[9],"high-quality":[10,25],"speech":[12,27,57,69,75,82,98,124,129,162,178],"impersonating":[13],"any":[14],"human":[15],"speaker":[16],"are":[17],"easily":[18],"available.":[19],"Several":[20],"incidents":[21],"report":[22],"misuse":[23],"of":[24,96,122,157,164],"for":[28,32,41,80],"spreading":[29],"misinformation":[30],"and":[31,118,140],"large-scale":[33],"financial":[34],"frauds.":[35],"Many":[36],"methods":[37,79],"have":[38],"been":[39],"proposed":[40],"detecting":[42],"speech;":[44],"however,":[45],"there":[46],"is":[47,64],"limited":[48],"work":[49],"on":[50,159],"localizing":[51,160],"the":[52,56,67,88,93,97,115,119,150,155],"segments":[54,70,163],"within":[55],"signal.":[58,76,99],"In":[59,100],"this":[60,101],"work,":[61,102],"our":[62],"goal":[63],"localize":[66,127],"a":[72,123,144],"partially":[73],"Most":[77],"existing":[78,176],"localization":[83,179],"obtain":[84,137],"features":[85,112,139],"from":[86,113],"either":[87],"time":[89,116],"domain":[90,117],"waveform":[91],"or":[92],"spectrogram":[94,120],"representation":[95,121],"we":[103],"propose":[104],"Multi-Domain":[105],"ResNet":[106],"Transformer":[107],"(MDRT)":[108],"that":[109,170],"obtains":[110],"multi-domain":[111,138],"both":[114],"signal":[125],"segments.":[130],"MDRT":[131,158,171],"uses":[132],"transformer":[133],"neural":[134,146],"networks":[135],"processes":[141],"them":[142],"using":[143],"ResNet-style":[145],"network.":[147],"We":[148],"use":[149],"PartialSpoof":[151],"dataset":[152],"examine":[154],"performance":[156],"varying":[165],"duration.":[166],"Our":[167],"results":[168],"show":[169],"performs":[172],"better":[173],"than":[174],"several":[175],"methods.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
