{"id":"https://openalex.org/W4402111996","doi":"https://doi.org/10.21437/interspeech.2024-659","title":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","display_name":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111996","doi":"https://doi.org/10.21437/interspeech.2024-659"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-659","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-659","pdf_url":"https://www.isca-archive.org/interspeech_2024/truong24b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/truong24b_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091500888","display_name":"Duc-Tuan Truong","orcid":"https://orcid.org/0009-0002-1767-7598"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Duc-Tuan Truong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111964014","display_name":"Tuan Lam Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuan Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002145453","display_name":"Hieu-Thi Luong","orcid":"https://orcid.org/0000-0002-4772-5995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hieu-Thi Luong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091500888"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2352,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97515939,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"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":0.9936000108718872,"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":0.9886000156402588,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9182999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7728433609008789},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5143274068832397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.505188524723053},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4517768919467926},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3774723410606384},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13216128945350647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728433609008789},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5143274068832397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.505188524723053},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4517768919467926},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3774723410606384},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13216128945350647},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-659","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-659","pdf_url":"https://www.isca-archive.org/interspeech_2024/truong24b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/114611","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/114611","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-659","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-659","pdf_url":"https://www.isca-archive.org/interspeech_2024/truong24b_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320331617","display_name":"National Supercomputing Centre Singapore","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111996.pdf","grobid_xml":"https://content.openalex.org/works/W4402111996.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Recent":[0],"synthetic":[1,47,129],"speech":[2,48,130],"detectors":[3],"leveraging":[4],"the":[5,13,23,28,33,38,69,91,101,106,124],"Transformer":[6,34],"model":[7],"have":[8],"superior":[9],"performance":[10],"compared":[11],"to":[12,22,81],"convolutional":[14],"neural":[15],"network":[16],"counterparts.This":[17],"improvement":[18,126],"could":[19],"be":[20,50],"due":[21],"powerful":[24],"modeling":[25],"ability":[26],"of":[27,41,46,55,68],"multi-head":[29],"selfattention":[30],"(MHSA)":[31],"in":[32,52,111],"model,":[35],"which":[36],"learns":[37],"temporal":[39,60,119],"relationship":[40],"each":[42],"input":[43,70],"token.However,":[44],"artifacts":[45],"can":[49,104],"located":[51],"specific":[53],"regions":[54],"both":[56,118],"frequency":[57],"channels":[58],"and":[59,120],"segments,":[61],"while":[62],"MHSA":[63],"neglects":[64],"this":[65,72],"temporal-channel":[66],"dependency":[67],"sequence.In":[71],"work,":[73],"we":[74],"proposed":[75],"a":[76],"Temporal-Channel":[77],"Modeling":[78],"(TCM)":[79],"module":[80,103],"enhance":[82],"MHSA's":[83],"capability":[84],"for":[85,127],"capturing":[86],"temporalchannel":[87],"dependencies.Experimental":[88],"results":[89],"on":[90],"ASVspoof":[92],"2021":[93],"show":[94],"that":[95,116],"with":[96],"only":[97],"0.03M":[98],"additional":[99],"parameters,":[100],"TCM":[102],"outperform":[105],"state-of-the-art":[107],"system":[108],"by":[109],"9.25%":[110],"EER.Further":[112],"ablation":[113],"study":[114],"reveals":[115],"utilizing":[117],"channel":[121],"information":[122],"yields":[123],"most":[125],"detecting":[128],"1":[131],".":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}