{"id":"https://openalex.org/W282126772","doi":"https://doi.org/10.21437/interspeech.2010-25","title":"On the exploitation of hidden Markov models and linear dynamic models in a hybrid decoder architecture for continuous speech recognition","display_name":"On the exploitation of hidden Markov models and linear dynamic models in a hybrid decoder architecture for continuous speech recognition","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W282126772","doi":"https://doi.org/10.21437/interspeech.2010-25","mag":"282126772"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-25","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5034723709","display_name":"Volker Leutnant","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Volker Leutnant","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034723709"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02304557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2946","last_page":"2949"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"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":0.9334702491760254},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8347392082214355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7654552459716797},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5774034261703491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49290990829467773},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.49050968885421753},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4853614568710327},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4540579319000244},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4379274845123291},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.437014102935791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23545178771018982},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.21008244156837463}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9334702491760254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347392082214355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7654552459716797},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5774034261703491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49290990829467773},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.49050968885421753},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4853614568710327},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4540579319000244},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4379274845123291},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.437014102935791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23545178771018982},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.21008244156837463},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-25","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1003237493","https://openalex.org/W1561429093","https://openalex.org/W1561506132","https://openalex.org/W1599571506","https://openalex.org/W1979449467","https://openalex.org/W2001285045","https://openalex.org/W2083393647","https://openalex.org/W2124868070","https://openalex.org/W2149361029","https://openalex.org/W2151125621","https://openalex.org/W2151323943","https://openalex.org/W2155010316","https://openalex.org/W2164579587","https://openalex.org/W2541906951"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2194396582","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2379938888","https://openalex.org/W2566202039","https://openalex.org/W4233405330"],"abstract_inverted_index":{"Linear":[0],"dynamic":[1],"models":[2,15],"(LDMs)":[3],"have":[4],"been":[5],"shown":[6],"to":[7,12,106],"be":[8,97],"a":[9,36,42],"viable":[10],"alternative":[11],"hidden":[13],"Markov":[14],"(HMMs)":[16],"on":[17,55,60,71],"small-vocabulary":[18],"recognition":[19,58],"tasks,":[20],"such":[21],"as":[22],"phone":[23,43],"classification.":[24],"In":[25],"this":[26],"paper":[27],"we":[28,53],"investigate":[29],"various":[30],"statistical":[31],"model":[32,66,94,113],"combination":[33,67],"approaches":[34],"for":[35,103],"hybrid":[37,76],"HMM-LDM":[38],"recognizer,":[39],"resulting":[40],"in":[41,82,110],"classification":[44],"performance":[45,89],"that":[46],"outperforms":[47],"the":[48,61,65,75,79,83,88,91,104,111],"best":[49],"individual":[50],"classifier.":[51],"Further,":[52],"report":[54],"continuous":[56],"speech":[57],"experiments":[59],"AURORA4":[62],"corpus,":[63],"where":[64],"is":[68],"carried":[69],"out":[70],"wordgraph":[72],"rescoring.":[73],"While":[74],"system":[77,81],"improves":[78],"HMM":[80,93],"case":[84],"of":[85,90],"monophone":[86,100],"HMMs,":[87],"triphone":[92],"could":[95],"not":[96],"improved":[98],"by":[99],"LDMs,":[101],"asking":[102],"need":[105],"introduce":[107],"context-dependency":[108],"also":[109],"LDM":[112],"inventory.":[114]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}