{"id":"https://openalex.org/W4319862408","doi":"https://doi.org/10.1109/slt54892.2023.10022967","title":"HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch","display_name":"HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862408","doi":"https://doi.org/10.1109/slt54892.2023.10022967"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022967","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5050968038","display_name":"Tina Raissi","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tina Raissi","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636970","display_name":"Wei Zhou","orcid":"https://orcid.org/0009-0006-3754-8872"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","AppTek GmbH, Aachen, Germany","Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028362932","display_name":"Simon Berger","orcid":"https://orcid.org/0000-0003-1333-4029"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Berger","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","AppTek GmbH, Aachen, Germany","Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","AppTek GmbH, Aachen, Germany","Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","AppTek GmbH, Aachen, Germany","Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]},{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6135,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91444657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"294"},"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":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.9178245067596436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928156852722168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7616338729858398},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6525164842605591},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5294090509414673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4827408194541931},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.46004700660705566},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43465182185173035},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.42742520570755005},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37839651107788086},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.3745853900909424},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2667335271835327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21559128165245056},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.15098193287849426}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9178245067596436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928156852722168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7616338729858398},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6525164842605591},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5294090509414673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4827408194541931},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.46004700660705566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43465182185173035},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.42742520570755005},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37839651107788086},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3745853900909424},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2667335271835327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21559128165245056},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.15098193287849426},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022967","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G3574710255","display_name":null,"funder_award_id":"03ZU1106DA","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G3941827858","display_name":null,"funder_award_id":"SCHL2043/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1553004968","https://openalex.org/W1828163288","https://openalex.org/W1977434607","https://openalex.org/W2009150118","https://openalex.org/W2016185147","https://openalex.org/W2024200390","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2291282366","https://openalex.org/W2514741789","https://openalex.org/W2520160253","https://openalex.org/W2597757402","https://openalex.org/W2746192915","https://openalex.org/W2748816379","https://openalex.org/W2799923439","https://openalex.org/W2808939837","https://openalex.org/W2889282842","https://openalex.org/W2903382683","https://openalex.org/W2944255943","https://openalex.org/W2963587345","https://openalex.org/W3103005696","https://openalex.org/W3105532142","https://openalex.org/W3147187328","https://openalex.org/W3160551958","https://openalex.org/W3167895882","https://openalex.org/W4224518768","https://openalex.org/W4225302305","https://openalex.org/W4225741214","https://openalex.org/W4320006236","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6674330103"],"related_works":["https://openalex.org/W2161328464","https://openalex.org/W2382132287","https://openalex.org/W2741448314","https://openalex.org/W324399734","https://openalex.org/W2076166534","https://openalex.org/W2379938888","https://openalex.org/W2096837052","https://openalex.org/W2593596363","https://openalex.org/W2116722627","https://openalex.org/W2143650221"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,28,54],"compare":[4],"from-scratch":[5,62],"sequence-level":[6],"cross-entropy":[7],"(full-sum)":[8],"training":[9,64],"of":[10,61,100],"Hidden":[11],"Markov":[12],"Model":[13],"(HMM)":[14],"and":[15,42,78,86,90,104],"Connectionist":[16],"Temporal":[17],"Classification":[18],"(CTC)":[19],"topologies":[20],"for":[21,33,49],"automatic":[22],"speech":[23,40],"recognition":[24],"(ASR).":[25],"Besides":[26],"accuracy,":[27],"further":[29],"analyze":[30],"their":[31],"capability":[32],"generating":[34],"high-quality":[35],"time":[36],"alignment":[37,68],"between":[38],"the":[39,43,67],"signal":[41],"transcription,":[44],"which":[45],"can":[46],"be":[47],"crucial":[48],"many":[50],"subsequent":[51],"applications.":[52],"Moreover,":[53],"propose":[55],"several":[56],"methods":[57],"to":[58],"improve":[59],"convergence":[60],"full-sum":[63,106],"by":[65],"addressing":[66],"modeling":[69],"issue.":[70],"Systematic":[71],"comparison":[72],"is":[73],"conducted":[74],"on":[75],"both":[76,101],"Switchboard":[77],"LibriSpeech":[79],"corpora":[80],"across":[81],"CTC,":[82],"posterior":[83],"HMM":[84],"with":[85],"w/o":[87],"transition":[88],"probabilities,":[89],"standard":[91],"hybrid":[92],"HMM.":[93],"We":[94],"also":[95],"provide":[96],"a":[97],"detailed":[98],"analysis":[99],"Viterbi":[102],"forced-alignment":[103],"Baum-Welch":[105],"occupation":[107],"probabilities.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}