{"id":"https://openalex.org/W2748679025","doi":"https://doi.org/10.21437/interspeech.2018-1392","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","display_name":"Cold Fusion: Training Seq2Seq Models Together with Language Models","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2748679025","doi":"https://doi.org/10.21437/interspeech.2018-1392","mag":"2748679025"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1392","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/1708.06426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047764126","display_name":"Anuroop Sriram","orcid":"https://orcid.org/0000-0001-6295-7535"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anuroop Sriram","raw_affiliation_strings":["Baidu (China), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065707162","display_name":"Heewoo Jun","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heewoo Jun","raw_affiliation_strings":["Baidu (China), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090158590","display_name":"Sanjeev Satheesh","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanjeev Satheesh","raw_affiliation_strings":["Baidu (China), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu (China), Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103153292","display_name":"Adam Coates","orcid":"https://orcid.org/0000-0002-4004-1603"},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam Coates","raw_affiliation_strings":["Manchester Metropolitan University, Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Manchester Metropolitan University, Manchester, United Kingdom","institution_ids":["https://openalex.org/I11983389"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047764126"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":7.256,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97585916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"391"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8243209719657898},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8164515495300293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6883041262626648},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6827793121337891},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6066320538520813},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6007861495018005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5997653603553772},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5976083278656006},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5522949695587158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5273153185844421},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4925854802131653},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4861149787902832},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4546712636947632},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4222137928009033},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.42200303077697754},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4200981557369232},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21032676100730896},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12962743639945984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243209719657898},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8164515495300293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6883041262626648},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6827793121337891},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6066320538520813},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6007861495018005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5997653603553772},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5976083278656006},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5522949695587158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5273153185844421},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4925854802131653},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4861149787902832},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4546712636947632},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4222137928009033},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.42200303077697754},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4200981557369232},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21032676100730896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12962743639945984},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2018-1392","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1708.06426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.06426","pdf_url":"https://arxiv.org/pdf/1708.06426","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:2748679025","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.06426.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.1708.06426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.06426","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"},{"id":"mag:2963442512","is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=Syor6PRLf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.06426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.06426","pdf_url":"https://arxiv.org/pdf/1708.06426","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":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2748679025.pdf","grobid_xml":"https://content.openalex.org/works/W2748679025.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1591706642","https://openalex.org/W1915251500","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2193413348","https://openalex.org/W2259472270","https://openalex.org/W2284660317","https://openalex.org/W2525778437","https://openalex.org/W2550837020","https://openalex.org/W2949640717","https://openalex.org/W2949650786","https://openalex.org/W2949888546","https://openalex.org/W2950903920","https://openalex.org/W2951991713","https://openalex.org/W2952339051","https://openalex.org/W2953022181","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W1915251500","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2964308564","https://openalex.org/W2127141656","https://openalex.org/W2963362078","https://openalex.org/W2963403868","https://openalex.org/W2962760690","https://openalex.org/W2130942839","https://openalex.org/W2101105183","https://openalex.org/W1524333225","https://openalex.org/W2963341956","https://openalex.org/W2962784628","https://openalex.org/W2936774411","https://openalex.org/W2525778437","https://openalex.org/W2327501763","https://openalex.org/W1494198834","https://openalex.org/W2963240019","https://openalex.org/W179875071","https://openalex.org/W2901739041"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"(Seq2Seq)":[1],"models":[2,71],"with":[3,72],"attention":[4],"have":[5],"excelled":[6],"at":[7],"tasks":[8],"which":[9,50],"involve":[10],"generating":[11],"natural":[12],"language":[13,39,54,80],"sentences":[14],"such":[15],"as":[16],"machine":[17],"translation,":[18],"image":[19],"captioning":[20],"and":[21,58,86,89],"speech":[22,64],"recognition.":[23],"Performance":[24],"has":[25],"further":[26],"been":[27],"improved":[28],"by":[29],"leveraging":[30],"unlabeled":[31],"data,":[32],"often":[33],"in":[34],"the":[35,46,63,104],"form":[36],"of":[37,103],"a":[38,52,95],"model.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"present":[45],"Cold":[47,73],"Fusion":[48,74],"method,":[49],"leverages":[51],"pre-trained":[53],"model":[55],"during":[56],"training,":[57],"show":[59,68],"its":[60],"effectiveness":[61],"on":[62],"recognition":[65],"task.":[66],"We":[67],"that":[69],"Seq2Seq":[70],"are":[75],"able":[76],"to":[77,94],"better":[78,87],"utilize":[79],"information":[81],"enjoying":[82],"i)":[83],"faster":[84],"convergence":[85],"generalization,":[88],"ii)":[90],"almost":[91],"complete":[92],"transfer":[93],"new":[96],"domain":[97],"while":[98],"using":[99],"less":[100],"than":[101],"10%":[102],"labeled":[105],"training":[106],"data.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}