{"id":"https://openalex.org/W2605325951","doi":"https://doi.org/10.21437/eurospeech.1997-27","title":"The demiphone: an efficient subword unit for continuous speech recognition","display_name":"The demiphone: an efficient subword unit for continuous speech recognition","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W2605325951","doi":"https://doi.org/10.21437/eurospeech.1997-27","mag":"2605325951"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-27","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-27","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/103116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000792887","display_name":"Jos\u00e9 B. Mari\u00f1o","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 B. Marino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103745398","display_name":"Albin Nogueiras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albin Nogueiras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1215","last_page":"1218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9883000254631042,"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/coarticulation","display_name":"Coarticulation","score":0.8304128646850586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758307456970215},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7698744535446167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6600884795188904},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5992826819419861},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.571413516998291},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5377839207649231},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5259765982627869},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5147985816001892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437680244445801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3865599036216736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3245326280593872},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11042767763137817},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08632054924964905}],"concepts":[{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.8304128646850586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758307456970215},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7698744535446167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6600884795188904},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5992826819419861},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.571413516998291},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5377839207649231},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5259765982627869},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5147985816001892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437680244445801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3865599036216736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3245326280593872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11042767763137817},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08632054924964905},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/eurospeech.1997-27","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-27","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"},{"id":"pmh:oai:upcommons.upc.edu:2117/103116","is_oa":false,"landing_page_url":"https://hdl.handle.net/2117/103116","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:www.recercat.cat:2072/282935","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/103116","pdf_url":"http://hdl.handle.net/2117/103116","source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.5508","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.5508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gps-tsc.upc.es/veu/pubs/download/Mar97.ps.gz","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:www.recercat.cat:2072/282935","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/103116","pdf_url":"http://hdl.handle.net/2117/103116","source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2605325951.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2990278625","https://openalex.org/W1993499045","https://openalex.org/W1604595447","https://openalex.org/W4200613756","https://openalex.org/W2983489261","https://openalex.org/W2988239832","https://openalex.org/W2075885261","https://openalex.org/W2174601236","https://openalex.org/W3036714870","https://openalex.org/W2153098279"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"introduce":[4],"the":[5,29,40,48,51,63,105,131,141],"demiphone":[6,25,36,68],"as":[7,72],"a":[8,23,34,59,73,80,91,125,134],"contextual":[9],"phonetic":[10],"unit":[11,46],"for":[12,28,120],"continuous":[13,121],"speech":[14,122,135],"recognition.":[15],"A":[16],"phone":[17],"is":[18,124],"divided":[19],"into":[20],"two":[21],"parts:":[22],"left":[24,30],"that":[26,37,78,102],"accounts":[27],"side":[31,42,55],"coarticulation":[32],"and":[33,88,111,114],"right":[35,41],"copes":[38],"with":[39],"context.":[43],"This":[44],"new":[45],"discards":[47],"dependence":[49],"between":[50,65],"effects":[52],"of":[53,62,76,84,108,133,149],"both":[54],"contexts,":[56],"but":[57],"provides":[58],"better":[60],"training":[61,83],"transition":[64],"phones.":[66],"The":[67],"can":[69],"be":[70],"seen":[71],"heuristic":[74],"clustering":[75],"states":[77],"allows":[79],"more":[81],"smoothed":[82],"hidden":[85],"Markov":[86,146],"models":[87,147],"additionally":[89],"supplies":[90],"simple":[92],"way":[93],"to":[94],"create":[95],"unseen":[96],"triphones.":[97],"We":[98],"report":[99],"experimental":[100],"evidence":[101],"demiphones":[103],"outperform":[104],"usual":[106],"combination":[107],"triphones,":[109],"right-side":[110],"left-side":[112],"biphones":[113],"monophones.":[115],"1.":[116],"INTRODUCTION":[117],"Acoustic":[118],"modeling":[119,143],"recognition":[123,136],"topic":[126],"under":[127],"permanent":[128],"research,":[129],"because":[130],"performance":[132],"system":[137],"greatly":[138],"depends":[139],"on":[140],"acoustic":[142],"quality.":[144],"Hidden":[145],"(HMM)":[148],"phones":[150],"are":[151],"...":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
