{"id":"https://openalex.org/W2773824886","doi":"https://doi.org/10.1109/asru.2017.8268967","title":"Learning modality-invariant representations for speech and images","display_name":"Learning modality-invariant representations for speech and images","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2773824886","doi":"https://doi.org/10.1109/asru.2017.8268967","mag":"2773824886"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268967","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/1712.03897","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043739265","display_name":"Kenneth Leidal","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Leidal","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, Cambridge, MA, USA","Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, Cambridge, MA, USA","Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, Cambridge, MA, USA","Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13929093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"424","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980999827384949,"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/embedding","display_name":"Embedding","score":0.6849161982536316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6538087129592896},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6524484157562256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6440451741218567},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5424633026123047},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5172341465950012},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5161253213882446},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4545530378818512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44887450337409973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3679564595222473},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2810360789299011}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6849161982536316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6538087129592896},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6524484157562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6440451741218567},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5424633026123047},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5172341465950012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5161253213882446},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4545530378818512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44887450337409973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3679564595222473},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2810360789299011},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru.2017.8268967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268967","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.03897","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03897","pdf_url":"https://arxiv.org/pdf/1712.03897","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":"","raw_type":"text"},{"id":"mag:2773824886","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1712.03897.pdf","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.1712.03897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.03897","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:1712.03897","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03897","pdf_url":"https://arxiv.org/pdf/1712.03897","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2773824886.pdf","grobid_xml":"https://content.openalex.org/works/W2773824886.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2029827332","https://openalex.org/W2112796928","https://openalex.org/W2187089797","https://openalex.org/W2544224704","https://openalex.org/W2556930864","https://openalex.org/W2561035176","https://openalex.org/W2593768305","https://openalex.org/W2605762339","https://openalex.org/W2799772357","https://openalex.org/W2949987290","https://openalex.org/W2951004968","https://openalex.org/W2962850167","https://openalex.org/W2963826681","https://openalex.org/W6631362777","https://openalex.org/W6637618735","https://openalex.org/W6639480849","https://openalex.org/W6721087566","https://openalex.org/W6729831399","https://openalex.org/W6729977899","https://openalex.org/W6730043537"],"related_works":["https://openalex.org/W2962732076","https://openalex.org/W2940957522","https://openalex.org/W2972711888","https://openalex.org/W2623164477","https://openalex.org/W2997918867","https://openalex.org/W2111692687","https://openalex.org/W3045310389","https://openalex.org/W43954826","https://openalex.org/W3161061950","https://openalex.org/W3111733255","https://openalex.org/W3114005958","https://openalex.org/W2917742317","https://openalex.org/W3194043616","https://openalex.org/W2896986545","https://openalex.org/W3021187248","https://openalex.org/W2963588142","https://openalex.org/W2731173046","https://openalex.org/W2899867883","https://openalex.org/W2901194007","https://openalex.org/W3037466839"],"abstract_inverted_index":{"In":[0,52,77],"this":[1,112,126],"paper,":[2],"we":[3,18],"explore":[4],"the":[5,21,36,60,100],"unsupervised":[6],"learning":[7,24],"of":[8,23,66,136],"a":[9,25,67,90],"semantic":[10,26,50,73,81,122],"embedding":[11],"space":[12,28],"for":[13,29],"co-occurring":[14,84],"sensory":[15],"inputs.":[16],"Specifically,":[17],"focus":[19],"on":[20],"task":[22],"vector":[27],"both":[30],"spoken":[31],"and":[32,38,45,62,140],"handwritten":[33],"digits":[34],"using":[35],"TIDIGITs":[37],"MNIST":[39],"datasets.":[40],"Current":[41],"techniques":[42],"encode":[43],"image":[44],"audio/textual":[46],"inputs":[47],"directly":[48],"to":[49,59,79,105,115,133],"embeddings.":[51],"contrast,":[53],"our":[54,86],"technique":[55,127],"maps":[56],"an":[57],"input":[58],"mean":[61],"log":[63],"variance":[64],"vectors":[65],"diagonal":[68],"Gaussian":[69],"from":[70,94],"which":[71,98],"sample":[72],"embeddings":[74,104],"are":[75],"drawn.":[76],"addition":[78],"encouraging":[80],"similarity":[82],"between":[83],"inputs,":[85],"loss":[87],"function":[88],"includes":[89],"regularization":[91,113],"term":[92,114],"borrowed":[93],"variational":[95],"autoencoders":[96],"(VAEs)":[97],"drives":[99],"posterior":[101],"distributions":[102],"over":[103],"be":[106,129],"unit":[107],"Gaussian.":[108],"We":[109,124],"can":[110],"use":[111],"filter":[116],"out":[117],"modality":[118],"information":[119,138],"while":[120],"preserving":[121],"information.":[123],"speculate":[125],"may":[128],"more":[130],"broadly":[131],"applicable":[132],"other":[134],"areas":[135],"cross-modality/domain":[137],"retrieval":[139],"transfer":[141],"learning.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
