{"id":"https://openalex.org/W2900312178","doi":"https://doi.org/10.1109/icassp.2019.8682750","title":"Multimodal Grounding for Sequence-to-sequence Speech Recognition","display_name":"Multimodal Grounding for Sequence-to-sequence Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2900312178","doi":"https://doi.org/10.1109/icassp.2019.8682750","mag":"2900312178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/1811.03865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103277328","display_name":"Ozan \u00c7a\u011flayan","orcid":"https://orcid.org/0000-0002-5992-3470"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ozan Caglayan","raw_affiliation_strings":["Le Mans University, Le Mans, France"],"affiliations":[{"raw_affiliation_string":"Le Mans University, Le Mans, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053704856","display_name":"Ramon Sanabria","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramon Sanabria","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036933477","display_name":"Shruti Palaskar","orcid":"https://orcid.org/0000-0001-8637-1897"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shruti Palaskar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043289060","display_name":"Lo\u00efc Barrault","orcid":"https://orcid.org/0000-0002-0634-6147"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Loic Barraul","raw_affiliation_strings":["Le Mans University, Le Mans, France"],"affiliations":[{"raw_affiliation_string":"Le Mans University, Le Mans, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103277328"],"corresponding_institution_ids":["https://openalex.org/I4210108471"],"apc_list":null,"apc_paid":null,"fwci":0.167,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40827754,"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":"8648","last_page":"8652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9990000128746033,"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":0.804053544998169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7092610597610474},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6124780774116516},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4913741648197174},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48935192823410034},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.45684587955474854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44308900833129883},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42548704147338867},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4239600896835327},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.42288050055503845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09631463885307312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804053544998169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7092610597610474},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6124780774116516},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4913741648197174},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48935192823410034},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45684587955474854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44308900833129883},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42548704147338867},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4239600896835327},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.42288050055503845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09631463885307312},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2019.8682750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.03865","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03865","pdf_url":"https://arxiv.org/pdf/1811.03865","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:2900312178","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1811.03865","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":"pmh:oai:HAL:hal-02431924v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02431924","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, France. pp.8648-8652, ⟨10.1109/ICASSP.2019.8682750⟩","raw_type":"Conference papers"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/74173","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/74173","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1811.03865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.03865","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:1811.03865","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03865","pdf_url":"https://arxiv.org/pdf/1811.03865","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":[{"id":"https://openalex.org/G1433134892","display_name":null,"funder_award_id":"ACI-154856","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2922803762","display_name":null,"funder_award_id":"45606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3355158854","display_name":null,"funder_award_id":"548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G367708065","display_name":null,"funder_award_id":"ACI-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3709464396","display_name":null,"funder_award_id":"-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3730782400","display_name":null,"funder_award_id":"1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3760515176","display_name":null,"funder_award_id":"ACI-1548562","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4244604461","display_name":"Multimodal Multilingual Continuous Representation for Human Language Understanding","funder_award_id":"ANR-15-CHR2-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7260934811","display_name":null,"funder_award_id":"CI-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G740863221","display_name":null,"funder_award_id":"FA8750-18-2-0018","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7683701006","display_name":null,"funder_award_id":"ANR-15-CHR2-0006-01","funder_id":"https://openalex.org/F4320338463","funder_display_name":"CHIST-ERA"},{"id":"https://openalex.org/G8293170275","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8430433013","display_name":null,"funder_award_id":"CHIST-ERA","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2900312178.pdf","grobid_xml":"https://content.openalex.org/works/W2900312178.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2048526313","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2399550240","https://openalex.org/W2463955103","https://openalex.org/W2512544816","https://openalex.org/W2514713644","https://openalex.org/W2551572271","https://openalex.org/W2581101319","https://openalex.org/W2586850765","https://openalex.org/W2619947201","https://openalex.org/W2623210963","https://openalex.org/W2714726990","https://openalex.org/W2732026016","https://openalex.org/W2798400235","https://openalex.org/W2885185669","https://openalex.org/W2899274165","https://openalex.org/W2914781455","https://openalex.org/W2919115771","https://openalex.org/W2952746495","https://openalex.org/W2962866381","https://openalex.org/W2962934715","https://openalex.org/W2963250244","https://openalex.org/W2964192290","https://openalex.org/W2964308564","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6640212811","https://openalex.org/W6679434410","https://openalex.org/W6712868603","https://openalex.org/W6726320248","https://openalex.org/W6740934225","https://openalex.org/W6746315900","https://openalex.org/W6755559483","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2964182350","https://openalex.org/W3163339532","https://openalex.org/W3131305672","https://openalex.org/W2766058732","https://openalex.org/W3200768929","https://openalex.org/W3155419065","https://openalex.org/W2992448548","https://openalex.org/W142758689","https://openalex.org/W3095773170","https://openalex.org/W2775304348","https://openalex.org/W2992632249","https://openalex.org/W1922655562","https://openalex.org/W2526425061","https://openalex.org/W2889624961","https://openalex.org/W2737108017","https://openalex.org/W2963785710","https://openalex.org/W3014973941","https://openalex.org/W3163462603","https://openalex.org/W2752238778","https://openalex.org/W1494243555"],"abstract_inverted_index":{"Humans":[0],"are":[1,164],"capable":[2],"of":[3,9,50,75,121,145,185],"processing":[4],"speech":[5,55],"by":[6,40,117],"making":[7],"use":[8],"multiple":[10],"sensory":[11],"modalities.":[12],"For":[13],"example,":[14],"the":[15,48,54,73,93,114,153,162,189],"environment":[16],"where":[17],"a":[18,65,119,183],"conversation":[19],"takes":[20],"place":[21],"generally":[22],"provides":[23],"semantic":[24],"and/or":[25],"acoustic":[26],"context":[27],"that":[28,132],"helps":[29],"us":[30],"to":[31,35,113,141],"resolve":[32],"ambiguities":[33],"or":[34],"recall":[36],"named":[37],"entities.":[38],"Motivated":[39],"this,":[41],"there":[42],"have":[43],"been":[44],"many":[45],"works":[46],"studying":[47],"integration":[49],"visual":[51,67,122],"information":[52],"into":[53],"recognition":[56],"pipeline.":[57],"Specifically,":[58],"in":[59,147,174],"our":[60],"previous":[61],"work,":[62],"we":[63,103],"propose":[64,104],"multistep":[66],"adaptive":[68,115,133,168],"training":[69,134],"approach":[70,116],"which":[71,187],"improves":[72],"accuracy":[74],"an":[76,97,142],"audio-based":[77],"Automatic":[78],"Speech":[79],"Recognition":[80],"(ASR)":[81],"system.":[82],"This":[83],"approach,":[84],"however,":[85],"is":[86,135,188],"not":[87],"end-to-end":[88,106,154,180],"as":[89],"it":[90],"requires":[91],"fine-tuning":[92],"whole":[94],"model":[95],"with":[96],"adaptation":[98],"layer.":[99],"In":[100],"this":[101],"paper,":[102],"novel":[105],"multimodal":[107],"ASR":[108],"systems":[109],"and":[110],"compare":[111],"them":[112],"using":[118],"range":[120],"representations":[123],"obtained":[124],"from":[125],"state-of-the-art":[126],"convolutional":[127],"neural":[128],"networks.":[129],"We":[130],"show":[131],"effective":[136],"for":[137,152],"S2S":[138],"models":[139,181],"leading":[140],"absolute":[143,171],"improvement":[144],"1.4%":[146],"word":[148],"error":[149],"rate.":[150],"As":[151],"systems,":[155],"although":[156],"they":[157],"perform":[158],"better":[159],"than":[160,167],"baseline,":[161],"improvements":[163],"slightly":[165],"less":[166],"training,":[169],"0.8":[170],"WER":[172,184],"reduction":[173],"single-best":[175],"models.":[176],"Using":[177],"ensemble":[178],"decoding,":[179],"reach":[182],"15%":[186],"lowest":[190],"score":[191],"among":[192],"all":[193],"systems.":[194]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}