{"id":"https://openalex.org/W3016053754","doi":"https://doi.org/10.1109/icassp40776.2020.9053010","title":"Full-Sum Decoding for Hybrid Hmm Based Speech Recognition Using LSTM Language Model","display_name":"Full-Sum Decoding for Hybrid Hmm Based Speech Recognition Using LSTM Language Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016053754","doi":"https://doi.org/10.1109/icassp40776.2020.9053010","mag":"3016053754"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, 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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, 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":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100636970"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83188755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7834","last_page":"7838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965999722480774,"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/decoding-methods","display_name":"Decoding methods","score":0.8782406449317932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766309976577759},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7354353666305542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6372750997543335},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6309583187103271},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5528603196144104},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5115590691566467},{"id":"https://openalex.org/keywords/sequential-decoding","display_name":"Sequential decoding","score":0.49874114990234375},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.48076698184013367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4597291052341461},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.41240188479423523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30297422409057617},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.16890540719032288}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8782406449317932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766309976577759},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7354353666305542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6372750997543335},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6309583187103271},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5528603196144104},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5115590691566467},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.49874114990234375},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.48076698184013367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4597291052341461},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.41240188479423523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30297422409057617},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.16890540719032288},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W1494198834","https://openalex.org/W1553004968","https://openalex.org/W2009150118","https://openalex.org/W2016185147","https://openalex.org/W2024200390","https://openalex.org/W2038462845","https://openalex.org/W2064675550","https://openalex.org/W2118774335","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2404974730","https://openalex.org/W2515801922","https://openalex.org/W2739090952","https://openalex.org/W2938348542","https://openalex.org/W2944255943","https://openalex.org/W2953561564","https://openalex.org/W2956159074","https://openalex.org/W2963660642","https://openalex.org/W2972528057","https://openalex.org/W2972692349","https://openalex.org/W3103005696","https://openalex.org/W4288290348","https://openalex.org/W6629717138","https://openalex.org/W6713561562","https://openalex.org/W6741670043","https://openalex.org/W6746515341","https://openalex.org/W6765658108"],"related_works":["https://openalex.org/W2147640366","https://openalex.org/W1900871934","https://openalex.org/W2109702161","https://openalex.org/W2185874953","https://openalex.org/W1646609213","https://openalex.org/W246155136","https://openalex.org/W3045295533","https://openalex.org/W40699615","https://openalex.org/W2367218571","https://openalex.org/W3014367939"],"abstract_inverted_index":{"In":[0],"hybrid":[1],"HMM":[2],"based":[3],"speech":[4],"recognition,":[5],"LSTM":[6],"language":[7],"models":[8,88],"have":[9],"been":[10],"widely":[11],"applied":[12,31],"and":[13,64,84,91,100,134],"achieved":[14,120],"large":[15],"improvements.":[16],"The":[17,75],"theoretical":[18],"capability":[19],"of":[20,45,61,107,137],"modeling":[21],"any":[22],"unlimited":[23],"context":[24],"suggests":[25],"that":[26],"no":[27],"recombination":[28],"should":[29],"be":[30],"in":[32,48,59,121],"decoding.":[33,49,139],"This":[34],"motivates":[35],"to":[36],"reconsider":[37],"full":[38],"summation":[39],"over":[40,116],"the":[41,52,66],"HMM-state":[42],"sequences":[43],"instead":[44],"Viterbi":[46],"approximation":[47],"We":[50,128],"explore":[51],"potential":[53],"gain":[54],"from":[55],"more":[56],"accurate":[57],"probabilities":[58],"terms":[60],"decision":[62,110],"making":[63],"apply":[65],"full-sum":[67,77,138],"decoding":[68,78,103],"with":[69],"a":[70],"modified":[71],"prefix-tree":[72],"search":[73],"framework.":[74],"proposed":[76],"is":[79],"evaluated":[80],"on":[81],"both":[82,98],"Switchboard":[83],"Librispeech":[85],"corpora.":[86],"Different":[87],"using":[89],"CE":[90],"sMBR":[92],"training":[93],"criteria":[94],"are":[95,112,119],"used.":[96],"Additionally,":[97],"MAP":[99],"confusion":[101],"network":[102],"as":[104],"approximated":[105],"variants":[106],"general":[108],"Bayes":[109],"rule":[111],"evaluated.":[113],"Consistent":[114],"improvements":[115],"strong":[117],"baselines":[118],"almost":[122],"all":[123],"cases":[124],"without":[125],"extra":[126],"cost.":[127],"also":[129],"discuss":[130],"tuning":[131],"effort,":[132],"efficiency":[133],"some":[135],"limitations":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}