{"id":"https://openalex.org/W2064114555","doi":"https://doi.org/10.1109/apsipa.2014.7041717","title":"Robust anchorperson detection based on audio streams using a hybrid I-vector and DNN system","display_name":"Robust anchorperson detection based on audio streams using a hybrid I-vector and DNN system","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2064114555","doi":"https://doi.org/10.1109/apsipa.2014.7041717","mag":"2064114555"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2014.7041717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","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/A5032551038","display_name":"Yun-Fan Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":true,"raw_author_name":"Yun-Fan Chang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023636029","display_name":"Payton Lin","orcid":"https://orcid.org/0000-0001-5462-6613"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Payton Lin","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070479315","display_name":"Shao-Hua Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Hua Cheng","raw_affiliation_strings":["Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102435172","display_name":"Kai-Hsuan Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Hsuan Chan","raw_affiliation_strings":["Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109452217","display_name":"Yi\u2010Chong Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chong Zeng","raw_affiliation_strings":["Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031804693","display_name":"Chia-Wei Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Wei Liao","raw_affiliation_strings":["Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048187223","display_name":"Wen-Tsung Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I3141939062","display_name":"Institute for Information Industry","ror":"https://ror.org/01d8kr740","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I3141939062"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Tsung Chang","raw_affiliation_strings":["Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Advanced Research Institute, Institute for Information Industry, Taipei, Taiwan","institution_ids":["https://openalex.org/I3141939062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060079796","display_name":"Yu-Chiang Wang","orcid":"https://orcid.org/0000-0003-2821-5022"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Yu-Chiang Wang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology, Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I29955533"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5032551038"],"corresponding_institution_ids":["https://openalex.org/I29955533","https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84749089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"4"},"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":0.9969000220298767,"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/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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":0.8449641466140747},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6292220950126648},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5740100145339966},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5730023384094238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5530961155891418},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.5094090104103088},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47727078199386597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4597272276878357},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4337821304798126},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.41636112332344055},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4127102196216583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1833447515964508},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10821762681007385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449641466140747},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6292220950126648},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5740100145339966},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5730023384094238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5530961155891418},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.5094090104103088},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47727078199386597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4597272276878357},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4337821304798126},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.41636112332344055},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4127102196216583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1833447515964508},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10821762681007385},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2014.7041717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","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":27,"referenced_works":["https://openalex.org/W90966543","https://openalex.org/W1758466134","https://openalex.org/W1950396994","https://openalex.org/W1957665339","https://openalex.org/W1985043720","https://openalex.org/W1993482042","https://openalex.org/W1993882792","https://openalex.org/W2008957275","https://openalex.org/W2033289482","https://openalex.org/W2041823554","https://openalex.org/W2070176749","https://openalex.org/W2072128103","https://openalex.org/W2073272735","https://openalex.org/W2098655860","https://openalex.org/W2105885996","https://openalex.org/W2125787953","https://openalex.org/W2140833774","https://openalex.org/W2150769028","https://openalex.org/W2151834591","https://openalex.org/W2151899309","https://openalex.org/W2165880886","https://openalex.org/W2168026884","https://openalex.org/W4231109964","https://openalex.org/W6640828828","https://openalex.org/W6667507107","https://openalex.org/W6678805908","https://openalex.org/W6680887930"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2591697403","https://openalex.org/W2372625757","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W4313178214","https://openalex.org/W4252379076","https://openalex.org/W3044690502","https://openalex.org/W2555630001"],"abstract_inverted_index":{"Anchorperson":[0,11],"segment":[1],"detection":[2,12,47,169],"enables":[3],"efficient":[4],"video":[5,53],"content":[6],"indexing":[7],"for":[8,100],"information":[9],"retrieval.":[10],"based":[13,48],"on":[14,49],"audio":[15,50,68,107,164],"analysis":[16],"has":[17],"gained":[18],"popularity":[19],"due":[20],"to":[21,44,61,82,104,120,160],"lower":[22],"computational":[23],"complexity":[24],"and":[25,38,144],"satisfactory":[26],"performance.":[27],"This":[28],"paper":[29],"presents":[30],"a":[31,35,76],"robust":[32,101],"framework":[33],"using":[34],"hybrid":[36,98,130,142],"I-vector":[37,60,143],"deep":[39],"neural":[40],"network":[41],"(DNN)":[42],"system":[43,57,99,138,153],"perform":[45],"anchorperson":[46,86,115,168],"streams":[51],"of":[52,127],"content.":[54],"The":[55],"proposed":[56,129,137,152],"first":[58],"applies":[59],"extract":[62],"speaker":[63,73],"identity":[64,74],"features":[65],"from":[66],"the":[67,71,84,97,106,122,128,136,140,151,163],"data.":[69],"With":[70],"extracted":[72],"features,":[75],"DNN":[77],"classifier":[78],"is":[79,94],"then":[80],"used":[81],"verify":[83],"claimed":[85],"identity.":[87],"In":[88],"addition,":[89],"subspace":[90],"feature":[91,102],"normalization":[92],"(SFN)":[93],"incorporated":[95],"into":[96],"extraction":[103],"compensate":[105,162],"mismatch":[108,165],"issues":[109,166],"caused":[110],"by":[111,157],"recording":[112],"devices.":[113],"An":[114],"verification":[116],"experiment":[117],"was":[118,154],"conducted":[119],"evaluate":[121],"equal":[123],"error":[124],"rate":[125],"(EER)":[126],"system.":[131,149],"Experimental":[132],"results":[133],"demonstrate":[134],"that":[135],"outperforms":[139],"state-of-the-art":[141],"support":[145],"vector":[146],"machine":[147],"(SVM)":[148],"Moreover,":[150],"further":[155],"enhanced":[156],"integrating":[158],"SFN":[159],"effectively":[161],"in":[167],"tasks.":[170]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}