{"id":"https://openalex.org/W4391021447","doi":"https://doi.org/10.1109/asru57964.2023.10389749","title":"End-To-End Training of a Neural HMM with Label and Transition Probabilities","display_name":"End-To-End Training of a Neural HMM with Label and Transition Probabilities","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021447","doi":"https://doi.org/10.1109/asru57964.2023.10389749"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5068803145","display_name":"Daniel Mann","orcid":"https://orcid.org/0000-0003-0206-289X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel Mann","raw_affiliation_strings":["AppTek GmbH,Aachen,Germany,52062"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH,Aachen,Germany,52062","institution_ids":[]}]},{"author_position":"middle","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,Machine Learning and Human Language Technology, Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Machine Learning and Human Language Technology, Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029547617","display_name":"Wilfried Michel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilfried Michel","raw_affiliation_strings":["AppTek GmbH,Aachen,Germany,52062"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH,Aachen,Germany,52062","institution_ids":[]}]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["AppTek GmbH,Aachen,Germany,52062","Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH,Aachen,Germany,52062","institution_ids":[]},{"raw_affiliation_string":"Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Aachen, 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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["AppTek GmbH,Aachen,Germany,52062","Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"AppTek GmbH,Aachen,Germany,52062","institution_ids":[]},{"raw_affiliation_string":"Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068803145"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5237,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73172671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983000159263611,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9182252883911133},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.863074541091919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7437458634376526},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.6357570290565491},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5640255212783813},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5619377493858337},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5354262590408325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5137901902198792},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5120882987976074},{"id":"https://openalex.org/keywords/forward-algorithm","display_name":"Forward algorithm","score":0.505681037902832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49741557240486145},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4885488450527191},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4439539909362793},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.38388150930404663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3648655116558075},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.21700304746627808}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9182252883911133},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.863074541091919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437458634376526},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.6357570290565491},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5640255212783813},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5619377493858337},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5354262590408325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5137901902198792},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5120882987976074},{"id":"https://openalex.org/C196455857","wikidata":"https://www.wikidata.org/wiki/Q5473264","display_name":"Forward algorithm","level":5,"score":0.505681037902832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49741557240486145},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4885488450527191},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4439539909362793},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.38388150930404663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3648655116558075},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.21700304746627808},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1494198834","https://openalex.org/W1513350018","https://openalex.org/W1531333757","https://openalex.org/W2009150118","https://openalex.org/W2024200390","https://openalex.org/W2086699924","https://openalex.org/W2095705004","https://openalex.org/W2102122585","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2131646590","https://openalex.org/W2140539590","https://openalex.org/W2150967358","https://openalex.org/W2161523118","https://openalex.org/W2166637769","https://openalex.org/W2291282366","https://openalex.org/W2746192915","https://openalex.org/W2748816379","https://openalex.org/W2903382683","https://openalex.org/W2936774411","https://openalex.org/W2962728618","https://openalex.org/W2964054038","https://openalex.org/W2981857663","https://openalex.org/W3025870691","https://openalex.org/W4224518768","https://openalex.org/W4225741214","https://openalex.org/W4236474156","https://openalex.org/W4296069265","https://openalex.org/W4319862408","https://openalex.org/W4385822519","https://openalex.org/W4385822992","https://openalex.org/W6631943919","https://openalex.org/W6674330103","https://openalex.org/W6681839825","https://openalex.org/W6684042573","https://openalex.org/W6757107679"],"related_works":["https://openalex.org/W1975869217","https://openalex.org/W2136652457","https://openalex.org/W4312943493","https://openalex.org/W2849436992","https://openalex.org/W1510894296","https://openalex.org/W2383829109","https://openalex.org/W2401728283","https://openalex.org/W2408529216","https://openalex.org/W2116722627","https://openalex.org/W2379938888"],"abstract_inverted_index":{"We":[0,95],"investigate":[1,85],"a":[2,44,62,71,110],"novel":[3],"modeling":[4],"approach":[5,49],"for":[6,33,55],"end-to-end":[7],"neural":[8],"network":[9],"training":[10,35,79,102],"using":[11],"hidden":[12,21],"Markov":[13],"models":[14,31],"(HMM)":[15],"where":[16],"the":[17,77,99,114],"transition":[18,83,100],"probabilities":[19,54],"between":[20,57],"states":[22],"are":[23,51,120],"modeled":[24],"and":[25,82,88],"learned":[26],"explicitly.":[27],"Most":[28],"contemporary":[29],"sequence-to-sequence":[30],"allow":[32],"from-scratch":[34],"by":[36],"summing":[37],"over":[38],"all":[39],"possible":[40],"label":[41,64,81],"segmentations":[42],"in":[43,126],"given":[45],"topology.":[46],"In":[47],"our":[48,93],"there":[50],"explicit,":[52],"learnable":[53],"transitions":[56],"segments":[58],"as":[59],"opposed":[60],"to":[61,122],"blank":[63],"that":[65,75,97],"implicitly":[66],"encodes":[67],"duration":[68],"statistics.We":[69],"implement":[70],"GPU-based":[72],"forward-backward":[73],"algorithm":[74],"enables":[76],"simultaneous":[78],"of":[80,92],"probabilities.We":[84],"recognition":[86,106],"results":[87],"additionally":[89],"Viterbi":[90,128],"alignments":[91,119],"models.":[94],"find":[96],"while":[98],"model":[101],"does":[103],"not":[104],"improve":[105],"performance,":[107],"it":[108],"has":[109],"positive":[111],"impact":[112],"on":[113],"alignment":[115],"quality.":[116],"The":[117],"generated":[118],"shown":[121],"be":[123],"viable":[124],"targets":[125],"state-of-the-art":[127],"trainings.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}