{"id":"https://openalex.org/W2153890400","doi":"https://doi.org/10.1109/asru.2009.5373462","title":"Multi-view learning of acoustic features for speaker recognition","display_name":"Multi-view learning of acoustic features for speaker recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2153890400","doi":"https://doi.org/10.1109/asru.2009.5373462","mag":"2153890400"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karen Livescu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041251496","display_name":"Mark Stoehr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Stoehr","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015602781"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1408,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.87830758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.828860342502594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7229199409484863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6189374327659607},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.5804823637008667},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5633193254470825},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.526746928691864},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49868297576904297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48508206009864807},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45322972536087036},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.45307302474975586},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4499717950820923},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.44891083240509033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4278259873390198},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4158666729927063},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06592068076133728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828860342502594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7229199409484863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6189374327659607},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.5804823637008667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5633193254470825},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.526746928691864},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49868297576904297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48508206009864807},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45322972536087036},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.45307302474975586},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4499717950820923},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.44891083240509033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4278259873390198},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4158666729927063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06592068076133728},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5373462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.411.8870","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.411.8870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/~klivescu/papers/livescu_stoehr_ASRU2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W57796367","https://openalex.org/W1536675765","https://openalex.org/W1550054889","https://openalex.org/W2025341678","https://openalex.org/W2037603696","https://openalex.org/W2042608483","https://openalex.org/W2048679005","https://openalex.org/W2100235303","https://openalex.org/W2137492562","https://openalex.org/W2138127867","https://openalex.org/W2142674578","https://openalex.org/W2152051032","https://openalex.org/W2165880886","https://openalex.org/W3127686677","https://openalex.org/W4237723258","https://openalex.org/W4285719527","https://openalex.org/W6602380046","https://openalex.org/W6633221178","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Abstract\u2014We":[0],"consider":[1,23],"learning":[2],"acoustic":[3,58,142],"feature":[4,143],"transformations":[5],"using":[6,81,149],"an":[7,70,141],"additional":[8],"view":[9],"of":[10,17,56,73,117,128],"the":[11,18,57,65,74,84,96,115,125,151],"data,":[12],"in":[13,26,90,99,133],"this":[14],"case":[15,116],"video":[16,31,66],"speaker\u2019s":[19],"face.":[20],"Specifically,":[21],"we":[22,104,111,130],"a":[24,77,118],"scenario":[25],"which":[27,129,134],"clean":[28],"audio":[29,43],"and":[30],"is":[32,44,124],"available":[33],"at":[34,38,145,153],"training":[35,146],"time,":[36,147],"while":[37,148],"test":[39,154],"time":[40],"only":[41,150],"noisy":[42,100],"available.":[45],"We":[46,68],"use":[47],"canonical":[48],"correlation":[49,63],"analysis":[50],"(CCA)":[51],"to":[52,114,139],"learn":[53,140],"linear":[54],"projections":[55],"observations":[59],"that":[60],"have":[61],"maximum":[62],"with":[64,92],"frames.":[67],"provide":[69],"initial":[71],"demonstration":[72],"approach":[75],"on":[76],"speaker":[78,120],"recognition":[79,121],"task":[80],"data":[82],"from":[83],"VidTIMIT":[85],"corpus.":[86],"The":[87,102],"projected":[88],"features,":[89],"combination":[91],"baseline":[93,97],"MFCCs,":[94],"outperform":[95],"recognizer":[98],"conditions.":[101],"techniques":[103],"present":[105],"are":[106,131,137],"quite":[107],"general,":[108],"although":[109],"here":[110],"apply":[112],"them":[113],"specific":[119],"task.":[122],"This":[123],"first":[126],"work":[127],"aware":[132],"multiple":[135],"views":[136],"used":[138],"projection":[144],"acoustics":[152],"time.":[155],"I.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}