{"id":"https://openalex.org/W2614371818","doi":"https://doi.org/10.1109/icassp.2018.8461977","title":"Learning Hard Alignments with Variational Inference","display_name":"Learning Hard Alignments with Variational Inference","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2614371818","doi":"https://doi.org/10.1109/icassp.2018.8461977","mag":"2614371818"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.05524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057996489","display_name":"Dieterich Lawson","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dieterich Lawson","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung-Cheng Chiu","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048032272","display_name":"George Tucker","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Tucker","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045077843","display_name":"Colin Raffel","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Raffel","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026208886","display_name":"Kevin Swersky","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Swersky","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112445699","display_name":"Navdeep Jaitly","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Navdeep Jaitly","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057996489"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.00204566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5799","last_page":"5803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/inference","display_name":"Inference","score":0.8058143854141235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7839535474777222},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7395458817481995},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6500738263130188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6137756109237671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5890851020812988},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5841625332832336},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.46005839109420776},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44990500807762146},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20069825649261475}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8058143854141235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839535474777222},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7395458817481995},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6500738263130188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6137756109237671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5890851020812988},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5841625332832336},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.46005839109420776},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44990500807762146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20069825649261475},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.05524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.05524","pdf_url":"https://arxiv.org/pdf/1705.05524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2614371818","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1705.05524.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.1705.05524","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.05524","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.05524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.05524","pdf_url":"https://arxiv.org/pdf/1705.05524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2614371818.pdf","grobid_xml":"https://content.openalex.org/works/W2614371818.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1779483307","https://openalex.org/W1956526898","https://openalex.org/W2077804127","https://openalex.org/W2108677974","https://openalex.org/W2115595010","https://openalex.org/W2119717200","https://openalex.org/W2122262818","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2178654303","https://openalex.org/W2204302769","https://openalex.org/W2278112683","https://openalex.org/W2327501763","https://openalex.org/W2396566817","https://openalex.org/W2499293415","https://openalex.org/W2510842514","https://openalex.org/W2523469089","https://openalex.org/W2529548870","https://openalex.org/W2950853958","https://openalex.org/W2951064684","https://openalex.org/W2951334113","https://openalex.org/W2951527505","https://openalex.org/W2952264928","https://openalex.org/W2953022181","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2890561216","https://openalex.org/W3210299434","https://openalex.org/W3160053372","https://openalex.org/W3179869055","https://openalex.org/W3163192937","https://openalex.org/W3093410019","https://openalex.org/W3090114880","https://openalex.org/W3021335241","https://openalex.org/W809730796","https://openalex.org/W2766272960","https://openalex.org/W2786277362","https://openalex.org/W2902711629","https://openalex.org/W2482453869","https://openalex.org/W2790443868","https://openalex.org/W121219881","https://openalex.org/W2966267855","https://openalex.org/W3134318682","https://openalex.org/W2586506233","https://openalex.org/W2610531930","https://openalex.org/W3214620264"],"abstract_inverted_index":{"There":[0],"has":[1],"recently":[2,94],"been":[3],"significant":[4],"interest":[5],"in":[6,120],"hard":[7,36,82],"attention":[8,22,28,37,83],"models":[9,38],"for":[10,84,137],"tasks":[11],"such":[12,29],"as":[13,30],"object":[14],"recognition,":[15],"visual":[16],"captioning":[17],"and":[18,54,68,97,122,125],"speech":[19],"recognition.":[20],"Hard":[21],"can":[23,39,63],"offer":[24],"benefits":[25],"over":[26],"soft":[27],"decreased":[31],"computational":[32],"cost,":[33],"but":[34,60],"training":[35],"be":[40,69],"difficult":[41],"because":[42],"of":[43,80],"the":[44,78,93,133],"discrete":[45],"latent":[46],"variables":[47],"they":[48],"introduce.":[49],"Previous":[50],"work":[51],"used":[52],"REINFORCE":[53],"Q-learning":[55],"to":[56,71,108],"approach":[57],"these":[58],"issues,":[59],"those":[61],"methods":[62],"provide":[64],"high-variance":[65],"gradient":[66],"estimates":[67],"slow":[70],"train.":[72],"In":[73],"this":[74,109],"paper,":[75],"we":[76,100],"tackle":[77],"problem":[79],"learning":[81],"a":[85,102,116,138],"sequential":[86],"task":[87,119],"using":[88],"variational":[89],"inference":[90],"methods,":[91],"specifically":[92],"introduced":[95],"VIMCO":[96,107],"NVIL.":[98],"Furthermore,":[99],"propose":[101],"novel":[103],"baseline":[104],"that":[105,127],"adapts":[106],"setting.":[110],"We":[111],"demonstrate":[112],"our":[113,128],"method":[114,129],"on":[115],"phoneme":[117],"recognition":[118],"clean":[121],"noisy":[123],"environments":[124],"show":[126],"outperforms":[130],"REINFORCE,":[131],"with":[132],"difference":[134],"being":[135],"greater":[136],"more":[139],"complicated":[140],"task.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}