{"id":"https://openalex.org/W4226031090","doi":"https://doi.org/10.21437/interspeech.2022-11276","title":"Better Intermediates Improve CTC Inference","display_name":"Better Intermediates Improve CTC Inference","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226031090","doi":"https://doi.org/10.21437/interspeech.2022-11276"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11276","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11276","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["LINE Corporation,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034965022","display_name":"Jaesong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesong Lee","raw_affiliation_strings":["NAVER Corporation,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Corporation,","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065076995","display_name":"Lukas Jyuhn\u2010Hsiarn Lee","orcid":"https://orcid.org/0000-0003-1095-6877"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lukas Lee","raw_affiliation_strings":["NAVER Corporation,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Corporation,","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["LINE Corporation,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113730169"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37257251,"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":"4965","last_page":"4969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.9865000247955322,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9728999733924866,"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":0.660912275314331},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6577134132385254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32978516817092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660912275314331},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6577134132385254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32978516817092896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11276","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11276","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1710082047","https://openalex.org/W1828163288","https://openalex.org/W2193413348","https://openalex.org/W2407080277","https://openalex.org/W2766219058","https://openalex.org/W2767206889","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963434219","https://openalex.org/W2972818416","https://openalex.org/W2996843693","https://openalex.org/W3015960524","https://openalex.org/W3035445001","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3112157188","https://openalex.org/W3162249256","https://openalex.org/W3163793923","https://openalex.org/W3169714379","https://openalex.org/W3172862365","https://openalex.org/W3197140813","https://openalex.org/W4294619240"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0],"paper":[1,15],"proposes":[2],"a":[3,21,29,34],"method":[4],"for":[5,67],"improved":[6],"CTC":[7,19,81],"inference":[8,66,83],"with":[9,24,56,89],"searched":[10],"intermediates":[11],"and":[12,32,84],"multi-pass":[13],"conditioning.The":[14],"first":[16],"formulates":[17],"self-conditioned":[18,80],"as":[20,28],"probabilistic":[22],"model":[23],"an":[25],"intermediate":[26,50,54],"prediction":[27],"latent":[30],"representation":[31],"provides":[33],"tractable":[35],"conditioning":[36,42,51,60,68,76],"framework.We":[37],"then":[38],"propose":[39],"two":[40],"new":[41,47,72],"methods":[43],"based":[44],"on":[45],"the":[46,69,78,86,90,99,107],"formulation:(1)":[48],"Searched":[49],"that":[52,61],"refines":[53],"predictions":[55,63],"beam-search,":[57],"(2)":[58],"Multi-pass":[59],"uses":[62],"of":[64],"previous":[65],"next":[70],"inference.These":[71],"approaches":[73],"enable":[74],"better":[75],"than":[77],"original":[79,108],"during":[82],"improve":[85],"final":[87],"performance.Experiments":[88],"LibriSpeech":[91],"dataset":[92],"show":[93],"relative":[94],"3%/12%":[95],"performance":[96],"improvement":[97],"at":[98],"maximum":[100],"in":[101],"test":[102],"clean/other":[103],"sets":[104],"compared":[105],"to":[106],"selfconditioned":[109],"CTC.":[110]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}