{"id":"https://openalex.org/W2963693044","doi":"https://doi.org/10.21437/interspeech.2017-1581","title":"Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis","display_name":"Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963693044","doi":"https://doi.org/10.21437/interspeech.2017-1581","mag":"2963693044"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1581","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","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/A5101986528","display_name":"Qingming Tang","orcid":"https://orcid.org/0000-0002-2670-4917"},"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":"Qingming Tang","raw_affiliation_strings":["Toyota Technological Institute at Chicago, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"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":"Weiran Wang","raw_affiliation_strings":["Toyota Technological Institute at Chicago, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, 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, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101986528"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":2.02352127,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.87527624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9976999759674072,"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":0.9976000189781189,"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/canonical-correlation","display_name":"Canonical correlation","score":0.8997447490692139},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6270856261253357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6070766448974609},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5615846514701843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.54218989610672},{"id":"https://openalex.org/keywords/canonical-analysis","display_name":"Canonical analysis","score":0.49380263686180115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42895931005477905},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4246498942375183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37800830602645874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25994834303855896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22656449675559998}],"concepts":[{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.8997447490692139},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6270856261253357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6070766448974609},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5615846514701843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54218989610672},{"id":"https://openalex.org/C75806538","wikidata":"https://www.wikidata.org/wiki/Q5033360","display_name":"Canonical analysis","level":2,"score":0.49380263686180115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42895931005477905},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4246498942375183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37800830602645874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25994834303855896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22656449675559998},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.21437/interspeech.2017-1581","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W137009889","https://openalex.org/W900447646","https://openalex.org/W1484147505","https://openalex.org/W1522301498","https://openalex.org/W1523385540","https://openalex.org/W1524333225","https://openalex.org/W1531883353","https://openalex.org/W1571599052","https://openalex.org/W1665214252","https://openalex.org/W1883346539","https://openalex.org/W1924770834","https://openalex.org/W1949478088","https://openalex.org/W1959608418","https://openalex.org/W2016538560","https://openalex.org/W2022799064","https://openalex.org/W2063036810","https://openalex.org/W2095705004","https://openalex.org/W2125290066","https://openalex.org/W2142074148","https://openalex.org/W2165712214","https://openalex.org/W2271840356","https://openalex.org/W2295584157","https://openalex.org/W2521028896","https://openalex.org/W2530846021","https://openalex.org/W2550200318","https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2962808998","https://openalex.org/W2962914230","https://openalex.org/W4237723258","https://openalex.org/W4294568686","https://openalex.org/W4320013936","https://openalex.org/W4394670483"],"related_works":["https://openalex.org/W2121524531","https://openalex.org/W1565185441","https://openalex.org/W302711736","https://openalex.org/W2174400750","https://openalex.org/W1968846550","https://openalex.org/W2367413540","https://openalex.org/W1970646221","https://openalex.org/W2389459357","https://openalex.org/W3127253221","https://openalex.org/W2354853260"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,9,94],"problem":[3],"of":[4,96],"acoustic":[5],"feature":[6,20,61,90,105],"learning":[7,21,91,106],"in":[8],"setting":[10],"where":[11],"we":[12],"have":[13],"access":[14],"to":[15,56],"another":[16],"(non-acoustic)":[17],"modality":[18],"for":[19,40,59,111],"but":[22],"not":[23],"at":[24],"test":[25],"time.We":[26],"use":[27],"deep":[28,37],"variational":[29,73],"canonical":[30],"correlation":[31],"analysis":[32],"(VCCA),":[33],"a":[34,72],"recently":[35],"proposed":[36],"generative":[38],"method":[39],"multi-view":[41,60],"representation":[42],"learning.We":[43],"also":[44],"extend":[45],"VCCA":[46,84],"with":[47,53,88],"improved":[48],"latent":[49,68],"variable":[50,69],"priors":[51],"and":[52,71,85,101],"adversarial":[54],"learning.Compared":[55],"other":[57],"techniques":[58],"learning,":[62],"VCCA's":[63],"advantages":[64],"include":[65],"an":[66],"intuitive":[67],"interpretation":[70],"lower":[74],"bound":[75],"objective":[76],"that":[77,103],"can":[78],"be":[79],"trained":[80],"end-to-end":[81],"efficiently.We":[82],"compare":[83],"its":[86],"extensions":[87],"previous":[89,109],"methods":[92,110],"on":[93],"University":[95],"Wisconsin":[97],"X-ray":[98],"Microbeam":[99],"Database,":[100],"show":[102],"VCCA-based":[104],"improves":[107],"over":[108],"speaker-independent":[112],"phonetic":[113],"recognition.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}