{"id":"https://openalex.org/W3027415810","doi":"https://doi.org/10.21437/interspeech.2020-2004","title":"Learning Joint Articulatory-Acoustic Representations with Normalizing Flows","display_name":"Learning Joint Articulatory-Acoustic Representations with Normalizing Flows","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3027415810","doi":"https://doi.org/10.21437/interspeech.2020-2004","mag":"3027415810"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2004","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.09463","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109583051","display_name":"Pramit Saha","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pramit Saha","raw_affiliation_strings":[", University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071585967","display_name":"Sidney Fels","orcid":"https://orcid.org/0000-0001-9279-9021"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sidney Fels","raw_affiliation_strings":[", University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.04446789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3196","last_page":"3200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8236949443817139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.638698160648346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5927239060401917},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5854041576385498},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.49653321504592896},{"id":"https://openalex.org/keywords/articulator","display_name":"Articulator","score":0.48130670189857483},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4189613163471222},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4162767827510834},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4130953550338745},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22618800401687622},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07475459575653076}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8236949443817139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.638698160648346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5927239060401917},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5854041576385498},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.49653321504592896},{"id":"https://openalex.org/C2778415344","wikidata":"https://www.wikidata.org/wiki/Q443216","display_name":"Articulator","level":2,"score":0.48130670189857483},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4189613163471222},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4162767827510834},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4130953550338745},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22618800401687622},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07475459575653076},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C29694066","wikidata":"https://www.wikidata.org/wiki/Q118301","display_name":"Orthodontics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2004","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.09463","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09463","pdf_url":"https://arxiv.org/pdf/2005.09463","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3027415810","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.09463","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.09463","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.09463","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.09463","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09463","pdf_url":"https://arxiv.org/pdf/2005.09463","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334506","display_name":"Canadian Institutes of Health Research","ror":"https://ror.org/01gavpb45"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3027415810.pdf","grobid_xml":"https://content.openalex.org/works/W3027415810.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W299440670","https://openalex.org/W1581928298","https://openalex.org/W1583912456","https://openalex.org/W2000721204","https://openalex.org/W2034829178","https://openalex.org/W2054159638","https://openalex.org/W2120847449","https://openalex.org/W2136655611","https://openalex.org/W2191779130","https://openalex.org/W2409550820","https://openalex.org/W2696259631","https://openalex.org/W2949120115","https://openalex.org/W2950893734","https://openalex.org/W2951004968","https://openalex.org/W2963091558","https://openalex.org/W2963139417","https://openalex.org/W2963403868","https://openalex.org/W3005556965","https://openalex.org/W3006076983","https://openalex.org/W3039319660","https://openalex.org/W3189765989"],"related_works":["https://openalex.org/W3094929307","https://openalex.org/W2086109316","https://openalex.org/W2909162762","https://openalex.org/W1926738958","https://openalex.org/W2415687683","https://openalex.org/W2080261932","https://openalex.org/W2069618035","https://openalex.org/W2994459744","https://openalex.org/W2021446425","https://openalex.org/W2112810316","https://openalex.org/W2083922760","https://openalex.org/W2599283316","https://openalex.org/W26581775","https://openalex.org/W2129321698","https://openalex.org/W2088344125","https://openalex.org/W2998790278","https://openalex.org/W2063350367","https://openalex.org/W2991419544","https://openalex.org/W3047274034","https://openalex.org/W2125861410"],"abstract_inverted_index":{"The":[0],"articulatory":[1,36,87],"geometric":[2],"configurations":[3],"of":[4,12,83,98,126],"the":[5,9,13,35,51,78,95,99,128],"vocal":[6,80],"tract":[7,81],"and":[8,37,62,70,94],"acoustic":[10,38,91],"properties":[11],"resultant":[14],"speech":[15,101],"sound":[16],"are":[17],"considered":[18],"to":[19,66],"have":[20],"a":[21,30,58,74,84,123],"strong":[22],"causal":[23],"relationship.":[24],"This":[25],"paper":[26],"aims":[27],"at":[28],"finding":[29],"joint":[31,124],"latent":[32],"representation":[33,97],"between":[34,77],"domain":[39],"for":[40],"vowel":[41],"sounds":[42],"via":[43],"invertible":[44],"neural":[45],"network":[46],"models,":[47],"while":[48],"simultaneously":[49],"preserving":[50],"respective":[52],"domain-specific":[53],"features.":[54],"Our":[55,103],"model":[56,93],"utilizes":[57],"convolutional":[59],"autoencoder":[60],"architecture":[61],"normalizing":[63],"flow-based":[64],"models":[65],"allow":[67],"both":[68,110,127],"forward":[69],"inverse":[71],"mappings":[72],"in":[73,108,121],"semi-supervised":[75],"manner,":[76],"mid-sagittal":[79],"geometry":[82],"two":[85],"degrees-of-freedom":[86],"synthesizer":[88],"with":[89],"1D":[90],"wave":[92],"Mel-spectrogram":[96],"synthesized":[100],"sounds.":[102],"approach":[104],"achieves":[105],"satisfactory":[106],"performance":[107],"achieving":[109,122],"articulatory-to-acoustic":[111],"as":[112,114],"well":[113],"acoustic-to-articulatory":[115],"mapping,":[116],"thereby":[117],"demonstrating":[118],"our":[119],"success":[120],"encoding":[125],"domains.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
