{"id":"https://openalex.org/W2745596852","doi":"https://doi.org/10.21437/interspeech.2017-1683","title":"Comparison of Decoding Strategies for CTC Acoustic Models","display_name":"Comparison of Decoding Strategies for CTC Acoustic Models","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2745596852","doi":"https://doi.org/10.21437/interspeech.2017-1683","mag":"2745596852"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1683","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/1708.04469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028321737","display_name":"Thomas Zenkel","orcid":"https://orcid.org/0009-0002-2060-156X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thomas Zenkel","raw_affiliation_strings":[],"affiliations":[]},{"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, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046084081","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0002-4231-6543"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024736091","display_name":"Matthias Sperber","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Sperber","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065183855","display_name":"Sebastian St\u00fcker","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian St\u00fcker","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028321737"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7023,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92397967,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.7209866046905518},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6784906983375549},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6615332365036011},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6223692297935486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6059727668762207},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5604298114776611},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.535163402557373},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48691093921661377},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4676268696784973},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4446415305137634},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42916417121887207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3787916302680969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3544631898403168},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.229777991771698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1244475245475769},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07676312327384949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209866046905518},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6784906983375549},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6615332365036011},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6223692297935486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6059727668762207},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5604298114776611},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.535163402557373},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48691093921661377},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4676268696784973},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4446415305137634},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42916417121887207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3787916302680969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3544631898403168},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.229777991771698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1244475245475769},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07676312327384949},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2017-1683","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1708.04469","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.04469","pdf_url":"https://arxiv.org/pdf/1708.04469","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":null},{"id":"mag:2745596852","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1708.04469.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.1708.04469","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.04469","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":"doi:10.5445/ir/1000078394","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000078394","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.04469","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.04469","pdf_url":"https://arxiv.org/pdf/1708.04469","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":null},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"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/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/G7260934811","display_name":null,"funder_award_id":"CI-1548562","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/F4320309895","display_name":"Carl-Zeiss-Stiftung","ror":"https://ror.org/03ng4kg22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2745596852.pdf","grobid_xml":"https://content.openalex.org/works/W2745596852.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1533416326","https://openalex.org/W1710082047","https://openalex.org/W1736701665","https://openalex.org/W1904365287","https://openalex.org/W2102113734","https://openalex.org/W2109886035","https://openalex.org/W2127141656","https://openalex.org/W2263232528","https://openalex.org/W2395416438","https://openalex.org/W2395825834","https://openalex.org/W2525246036","https://openalex.org/W2525778437","https://openalex.org/W2559554776","https://openalex.org/W2577255746","https://openalex.org/W2594229957","https://openalex.org/W2608712415","https://openalex.org/W2951327905","https://openalex.org/W2952470929","https://openalex.org/W2953188895","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2963537349","https://openalex.org/W2127141656","https://openalex.org/W2102113734","https://openalex.org/W2327501763","https://openalex.org/W2890197052","https://openalex.org/W2972926005","https://openalex.org/W2951327905","https://openalex.org/W2526425061","https://openalex.org/W1586532344","https://openalex.org/W3097438275","https://openalex.org/W2082890803","https://openalex.org/W2921000669","https://openalex.org/W2043762869","https://openalex.org/W3015595164","https://openalex.org/W3168770049","https://openalex.org/W2125654400","https://openalex.org/W2785450052","https://openalex.org/W3127129631","https://openalex.org/W1606268232","https://openalex.org/W2991480510"],"abstract_inverted_index":{"Connectionist":[0],"Temporal":[1],"Classification":[2],"has":[3],"recently":[4],"attracted":[5],"a":[6,54,83,99,126,132],"lot":[7],"of":[8,32,40,47,68,89,128,139],"interest":[9],"as":[10],"it":[11],"offers":[12],"an":[13,29,37],"elegant":[14],"approach":[15],"to":[16,36,124],"building":[17],"acoustic":[18,69],"models":[19,120],"(AMs)":[20],"for":[21,86,103,152],"speech":[22,106],"recognition.":[23],"The":[24],"CTC":[25,51,90],"loss":[26],"function":[27],"maps":[28],"input":[30],"sequence":[31,39,127],"observable":[33],"feature":[34],"vectors":[35],"output":[38],"symbols.":[41],"Output":[42],"symbols":[43],"are":[44],"conditionally":[45],"independent":[46],"each":[48],"other":[49],"under":[50],"loss,":[52],"so":[53],"language":[55],"model":[56],"(LM)":[57],"can":[58,112,121],"be":[59,113,122],"incorporated":[60],"conveniently":[61],"during":[62],"decoding,":[63],"retaining":[64],"the":[65,137],"traditional":[66],"separation":[67],"and":[70,108,111,143,155],"linguistic":[71],"components":[72],"in":[73,157],"ASR.":[74],"For":[75],"fixed":[76],"vocabularies,":[77],"Weighted":[78],"Finite":[79],"State":[80],"Transducers":[81],"provide":[82,98],"strong":[84],"baseline":[85],"efficient":[87],"integration":[88],"AMs":[91],"with":[92,115],"n-gram":[93],"LMs.":[94],"Character-based":[95],"neural":[96],"LMs":[97],"straight":[100],"forward":[101],"solution":[102],"open":[104],"vocabulary":[105],"recognition":[107],"all-neural":[109],"models,":[110],"decoded":[114],"beam":[116],"search.":[117],"Finally,":[118],"sequence-to-sequence":[119],"used":[123],"translate":[125],"individual":[129],"sounds":[130],"into":[131],"word":[133],"string.":[134],"We":[135],"compare":[136],"performance":[138],"these":[140],"three":[141],"approaches,":[142],"analyze":[144],"their":[145],"error":[146],"patterns,":[147],"which":[148],"provides":[149],"insightful":[150],"guidance":[151],"future":[153],"research":[154],"development":[156],"this":[158],"important":[159],"area.":[160]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}