{"id":"https://openalex.org/W42131348","doi":"https://doi.org/10.21437/eurospeech.1997-21","title":"Creating large subword units for speech recognition","display_name":"Creating large subword units for speech recognition","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W42131348","doi":"https://doi.org/10.21437/eurospeech.1997-21","mag":"42131348"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-21","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-21","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5090343464","display_name":"Thilo Pfau","orcid":"https://orcid.org/0000-0002-0702-4289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thilo Pfau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103338437","display_name":"Manfred Beham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manfred Beham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034984518","display_name":"W. Reichl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W. Reichl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111883856","display_name":"G\u00fcnther Ruske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00fcnther Ruske","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00486821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1191","last_page":"1194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9898999929428101,"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":0.9898999929428101,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9186999797821045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8070582151412964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7877551913261414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7276265025138855},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6049389839172363},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6004213094711304},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46379926800727844},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.4499158561229706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43932825326919556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40548092126846313},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16270211338996887}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8070582151412964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877551913261414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7276265025138855},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6049389839172363},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6004213094711304},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46379926800727844},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.4499158561229706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43932825326919556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40548092126846313},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16270211338996887},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1997-21","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-21","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,74],"the":[4,42,58,61,66,77,91,97,108,115,122],"choice":[5],"of":[6,27,45,60,93,99],"suitable":[7],"subword":[8,31,50],"units":[9,51],"(SWU)":[10],"for":[11,41],"a":[12,86],"HMM":[13],"based":[14],"speech":[15],"recognition":[16],"system.":[17],"Using":[18],"demisyllables":[19],"(including":[20],"phonemes)":[21],"as":[22,128,130],"base":[23],"units,":[24,32],"an":[25,69],"inventory":[26,68],"domain-specific":[28],"larger":[29],"sized":[30],"so-called":[33],"macro-demisyllabes":[34],"(MDS),":[35],"is":[36,52,72,83],"created.":[37],"A":[38],"quality":[39,79],"measure":[40],"automatic":[43],"decomposition":[44],"all":[46],"single":[47],"words":[48],"into":[49,56],"presented":[53],"which":[54],"takes":[55],"account":[57],"trainability":[59],"chosen":[62],"units.":[63],"For":[64],"creating":[65],"whole":[67],"iterative":[70],"procedure":[71],"applied":[73],"respect":[75],"to":[76,107,140],"predefined":[78],"measure.":[80],"Each":[81],"MDS":[82,125,136],"represented":[84],"by":[85],"dedicated":[87],"HMM.":[88],"By":[89],"tying":[90],"densities":[92],"specific":[94],"phonemes,":[95],"only":[96],"number":[98],"mixture":[100],"coefficients":[101],"and":[102],"transitions":[103],"increases":[104],"in":[105],"comparison":[106],"original":[109],"phoneme":[110],"models.":[111],"Recognition":[112],"experiments":[113],"within":[114],"German":[116],"Verbmobil":[117],"evaluation":[118],"1996":[119],"show":[120],"that":[121],"new":[123],"simple":[124],"models":[126,137],"are":[127,138],"powerful":[129],"standard":[131],"triphone":[132],"models,":[133],"although":[134],"our":[135],"up":[139],"now":[141],"context-independent":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}