{"id":"https://openalex.org/W1529589667","doi":"https://doi.org/10.1109/icassp.1984.1172747","title":"Automatic diphone bootstrapping for speaker-adaptive continuous speech recognition","display_name":"Automatic diphone bootstrapping for speaker-adaptive continuous speech recognition","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W1529589667","doi":"https://doi.org/10.1109/icassp.1984.1172747","mag":"1529589667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1984.1172747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1984.1172747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '84. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073080869","display_name":"A.M. Colla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Colla","raw_affiliation_strings":["Elettronica San Giorgio, ELSAG S.p.A., Genova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elettronica San Giorgio, ELSAG S.p.A., Genova, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070854285","display_name":"D. Sciarra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Sciarra","raw_affiliation_strings":["Elettronica San Giorgio, ELSAG S.p.A., Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elettronica San Giorgio, ELSAG S.p.A., Genoa, Italy","institution_ids":[]}]}],"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"5","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":0.9975000023841858,"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":0.9975000023841858,"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":0.9871000051498413,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9079999923706055,"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/computer-science","display_name":"Computer science","score":0.8131775856018066},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8024536371231079},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5704026222229004},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5304479002952576},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5176361203193665},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4609317183494568},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4479753077030182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42648836970329285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40293505787849426},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06645679473876953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06308409571647644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131775856018066},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8024536371231079},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5704026222229004},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5304479002952576},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5176361203193665},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4609317183494568},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4479753077030182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42648836970329285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40293505787849426},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06645679473876953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06308409571647644},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1109/icassp.1984.1172747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1984.1172747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '84. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1565967034","https://openalex.org/W1703050006","https://openalex.org/W1774234760","https://openalex.org/W2019955916","https://openalex.org/W2074223539","https://openalex.org/W2113090100","https://openalex.org/W4230220154","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"The":[0,109],"paper":[1],"describes":[2],"an":[3,89],"automatic":[4,93],"method,":[5],"called":[6],"Automatic":[7],"Diphone":[8],"Bootstrapping":[9],"(or":[10],"A.D.B.),":[11],"for":[12,15,32,79,83,95,121],"template":[13,81],"extraction":[14,66,98],"Speaker-Adaptive":[16],"Continuous":[17],"Speech":[18],"Recognition":[19],"using":[20,143],"\"diphones\"":[21],"as":[22,34,73,88],"speech":[23],"units.":[24],"Diphones":[25],"have":[26],"proved":[27],"to":[28],"be":[29],"very":[30,59,119],"suitable":[31],"C.S.R.":[33,56],"they":[35,103],"meet":[36],"the":[37,45,50,71,74,123,144,149],"main":[38],"requirements":[39],"of":[40,52,138],"phonetic":[41],"units:":[42],"invariance":[43],"with":[44],"context":[46],"and":[47,117],"economy.":[48],"Furthermore":[49],"performance":[51],"diphone-based":[53],"speaker":[54,85],"dependent":[55],"systems":[57],"is":[58],"high.":[60],"For":[61],"a":[62,131,136],"long":[63],"time":[64],"manual":[65,107,115],"has":[67],"been":[68],"presented":[69],"in":[70],"literature":[72],"only":[75],"completely":[76],"reliable":[77],"method":[78],"sub-word":[80],"creation":[82],"any":[84,114],"(see":[86],"[1]":[87],"example).":[90],"Recently":[91],"some":[92,106],"techniques":[94],"reference":[96],"pattern":[97],"were":[99],"developed":[100],"[2,3],":[101],"but":[102],"also":[104],"require":[105],"corrections.":[108],"A.D.B.":[110,150],"procedure":[111],"operates":[112],"without":[113],"intervention":[116],"performed":[118],"well":[120],"all":[122],"speakers":[124],"on":[125],"which":[126],"it":[127],"was":[128,140],"tested.":[129],"In":[130],"connected":[132],"digit":[133],"recognition":[134],"task,":[135],"W.R.R.":[137],"98.79%":[139],"achieved":[141],"by":[142,148],"speaker-adaptive":[145],"templates":[146],"created":[147],"procedure.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
