{"id":"https://openalex.org/W2063036810","doi":"https://doi.org/10.1109/icassp.2013.6639047","title":"Multi-view CCA-based acoustic features for phonetic recognition across speakers and domains","display_name":"Multi-view CCA-based acoustic features for phonetic recognition across speakers and domains","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2063036810","doi":"https://doi.org/10.1109/icassp.2013.6639047","mag":"2063036810"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5063457506","display_name":"Raman Arora","orcid":"https://orcid.org/0000-0003-2002-3923"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raman Arora","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, IL, USA","Toyota Technol. Inst. at Chicago (TTIC), Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"Toyota Technol. Inst. at Chicago (TTIC), Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, IL, USA","Toyota Technol. Inst. at Chicago (TTIC), Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"Toyota Technol. Inst. at Chicago (TTIC), Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063457506"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":16.8043,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.99105913,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7135","last_page":"7139"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.9508935213088989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695079445838928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7316756248474121},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.6281276345252991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5204865336418152},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4596554636955261},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43010950088500977},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41221702098846436},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.23215916752815247},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10841366648674011}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.9508935213088989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695079445838928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7316756248474121},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.6281276345252991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5204865336418152},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4596554636955261},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43010950088500977},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41221702098846436},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.23215916752815247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10841366648674011},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.721","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.721","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/arora_livescu_ICASSP2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G3710792369","display_name":null,"funder_award_id":"IIS-0905633","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4566376420","display_name":"RI: Medium: Collaborative Research: Explicit Articulatory Models of Spoken Language, with Application to Automatic Speech Recognition","funder_award_id":"0905633","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W30596880","https://openalex.org/W46785905","https://openalex.org/W98563929","https://openalex.org/W196476531","https://openalex.org/W1549321558","https://openalex.org/W1589867908","https://openalex.org/W1986194954","https://openalex.org/W1986317063","https://openalex.org/W1995615461","https://openalex.org/W2003890417","https://openalex.org/W2025341678","https://openalex.org/W2052382192","https://openalex.org/W2076455317","https://openalex.org/W2080400971","https://openalex.org/W2091650508","https://openalex.org/W2093886330","https://openalex.org/W2100235303","https://openalex.org/W2110121428","https://openalex.org/W2128422565","https://openalex.org/W2142674578","https://openalex.org/W2147284655","https://openalex.org/W2148226542","https://openalex.org/W2152051032","https://openalex.org/W2153890400","https://openalex.org/W2155277636","https://openalex.org/W2156204103","https://openalex.org/W2160594205","https://openalex.org/W2165712214","https://openalex.org/W2231075402","https://openalex.org/W2296654356","https://openalex.org/W2395955767","https://openalex.org/W2405732242","https://openalex.org/W2406820985","https://openalex.org/W3087819914","https://openalex.org/W3149375329","https://openalex.org/W4237723258","https://openalex.org/W6601897821","https://openalex.org/W6604005260","https://openalex.org/W6635242571","https://openalex.org/W6676539569","https://openalex.org/W6683444093","https://openalex.org/W6713704110","https://openalex.org/W6783563602"],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1669577408","https://openalex.org/W1994694193","https://openalex.org/W2161865195","https://openalex.org/W170831052","https://openalex.org/W4247725880","https://openalex.org/W1006721676","https://openalex.org/W2100854157","https://openalex.org/W2978471304","https://openalex.org/W1771058801"],"abstract_inverted_index":{"Canonical":[0],"correlation":[1],"analysis":[2],"(CCA)":[3],"and":[4,29,55,87,99,115,121,147],"kernel":[5],"CCA":[6],"can":[7],"be":[8],"used":[9,34],"for":[10,25],"unsupervised":[11],"learning":[12],"of":[13,45,52,76],"acoustic":[14,47,66,110],"features":[15,48,67,83,111,136],"when":[16],"a":[17],"second":[18],"view":[19],"(e.g.,":[20],"articulatory":[21],"measurements)":[22],"is":[23],"available":[24],"some":[26],"training":[27],"data,":[28,92],"such":[30],"projections":[31,155],"have":[32],"been":[33],"to":[35,57],"improve":[36],"phonetic":[37,53,124,142],"frame":[38],"classification.":[39],"Here":[40],"we":[41],"study":[42],"the":[43,50,74,108,153],"behavior":[44],"CCA-based":[46,135],"on":[49,90,96,145,149],"task":[51],"recognition,":[54],"investigate":[56],"what":[58],"extent":[59],"they":[60],"are":[61,68,84,127],"speaker-independent":[62],"or":[63,151],"domain-independent.":[64],"The":[65,82],"learned":[69,109,154],"using":[70,134],"data":[71],"drawn":[72],"from":[73],"University":[75],"Wisconsin":[77],"X-ray":[78],"Microbeam":[79],"Database":[80],"(XRMB).":[81],"evaluated":[85],"within":[86],"across":[88],"speakers":[89],"XRMB":[91,146],"as":[93,95],"well":[94],"out-of-domain":[97],"TIMIT":[98],"MOCHA-TIMIT":[100],"data.":[101],"Experimental":[102],"results":[103],"show":[104],"consistent":[105],"improvement":[106],"with":[107],"over":[112,137],"baseline":[113,138],"MFCCs":[114],"PCA":[116],"projections.":[117],"In":[118,140],"both":[119],"speaker-dependent":[120],"cross-speaker":[122],"experiments,":[123],"error":[125],"rates":[126],"improved":[128],"by":[129],"4-9%":[130],"absolute":[131],"(10-23%":[132],"relative)":[133],"MFCCs.":[139],"cross-domain":[141],"recognition":[143],"(training":[144],"testing":[148],"MOCHA":[150],"TIMIT),":[152],"provide":[156],"smaller":[157],"improvements.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}