{"id":"https://openalex.org/W2937023704","doi":"https://doi.org/10.1109/icassp.2019.8682573","title":"Audio Replay Spoof Attack Detection Using Segment-based Hybrid Feature and DenseNet-LSTM Network","display_name":"Audio Replay Spoof Attack Detection Using Segment-based Hybrid Feature and DenseNet-LSTM Network","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2937023704","doi":"https://doi.org/10.1109/icassp.2019.8682573","mag":"2937023704"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5086321795","display_name":"Lian Huang","orcid":"https://orcid.org/0000-0001-9222-9053"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Lian Huang","raw_affiliation_strings":["Department of Computer and Information Science, University of Macau, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772506","display_name":"Chi\u2010Man Pun","orcid":"https://orcid.org/0000-0003-1788-3746"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chi-Man Pun","raw_affiliation_strings":["Department of Computer and Information Science, University of Macau, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Macau, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":2.1869,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.9122583,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2567","last_page":"2571"},"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":0.9973999857902527,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8661150336265564},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8341177701950073},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6483761072158813},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6033917665481567},{"id":"https://openalex.org/keywords/replay-attack","display_name":"Replay attack","score":0.5889567732810974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5728217363357544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5258370637893677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5099281072616577},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5058571696281433},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.07006576657295227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8661150336265564},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8341177701950073},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6483761072158813},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6033917665481567},{"id":"https://openalex.org/C11560541","wikidata":"https://www.wikidata.org/wiki/Q1756025","display_name":"Replay attack","level":3,"score":0.5889567732810974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728217363357544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5258370637893677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5099281072616577},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5058571696281433},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.07006576657295227},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":18,"referenced_works":["https://openalex.org/W1638038541","https://openalex.org/W2041823554","https://openalex.org/W2042105302","https://openalex.org/W2123299109","https://openalex.org/W2141493634","https://openalex.org/W2176804518","https://openalex.org/W2194775991","https://openalex.org/W2303197844","https://openalex.org/W2312101546","https://openalex.org/W2515753980","https://openalex.org/W2585365199","https://openalex.org/W2607084024","https://openalex.org/W2735237710","https://openalex.org/W2747872086","https://openalex.org/W2785354100","https://openalex.org/W2810350850","https://openalex.org/W2963446712","https://openalex.org/W3198123200"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2836844603","https://openalex.org/W2138847091"],"abstract_inverted_index":{"At":[0],"present,":[1],"most":[2],"automatic":[3],"speaker":[4],"verification":[5],"(ASV)":[6],"systems":[7],"are":[8,55],"vulnerable":[9],"to":[10,85],"replay":[11,26],"spoof":[12,27],"attacks.":[13,28],"Therefore,":[14],"this":[15],"paper":[16],"proposes":[17],"a":[18,30,58],"new":[19],"approach":[20],"for":[21],"the":[22,40,73,81,86,91,98],"detection":[23],"of":[24,60],"audio":[25],"Here,":[29],"segment-based":[31],"hybrid":[32,53,69],"feature":[33],"extraction":[34],"method":[35,100],"is":[36],"used,":[37],"which":[38],"includes":[39],"Mel-frequency":[41],"cepstral":[42,48],"coefficient":[43],"(MFCC)":[44],"features":[45,54,78],"and":[46,67,93],"Constant-Q":[47],"coefficients":[49],"(CQCC)":[50],"features.":[51],"Then,":[52],"trained":[56],"using":[57,72],"variety":[59],"deep":[61],"learning":[62],"networks,":[63],"including":[64],"DenseNet,":[65],"LSTM,":[66],"DenseNet-LSTM":[68,74],"architectures.":[70],"Experiments":[71],"model":[75,96],"with":[76],"mixed":[77],"framework":[79],"achieves":[80],"best":[82],"performance.":[83],"Compared":[84],"baseline":[87],"system":[88],"built":[89],"on":[90],"CQCC":[92],"Gaussian":[94],"mixture":[95],"(GMM),":[97],"proposed":[99],"achieved":[101],"64.31%":[102],"relative":[103],"improvement.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}