{"id":"https://openalex.org/W2109089533","doi":"https://doi.org/10.1109/icassp.2002.5743743","title":"Improved duration control for speech synthesis using a multigram language model","display_name":"Improved duration control for speech synthesis using a multigram language model","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2109089533","doi":"https://doi.org/10.1109/icassp.2002.5743743","mag":"2109089533"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743743","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5021607001","display_name":"Matthias Eichner","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Eichner","raw_affiliation_strings":["Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Dresden, Germany","Dresden University of Technology, Laboratory of Acoustics and Speech Communication, D-01062, Germany"],"affiliations":[{"raw_affiliation_string":"Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Dresden University of Technology, Laboratory of Acoustics and Speech Communication, D-01062, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784693","display_name":"Matthias Wolff","orcid":"https://orcid.org/0000-0002-3895-7313"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Wolff","raw_affiliation_strings":["Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Dresden, Germany","Dresden University of Technology, Laboratory of Acoustics and Speech Communication, D-01062, Germany"],"affiliations":[{"raw_affiliation_string":"Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Dresden University of Technology, Laboratory of Acoustics and Speech Communication, D-01062, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103817232","display_name":"R\u00fcdiger Hoffmann","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rudiger Hoffmann","raw_affiliation_strings":["Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Dresden, Germany","Dresden University of Technology, Laboratory of Acoustics and Speech Communication, D-01062, Germany"],"affiliations":[{"raw_affiliation_string":"Laboratory of Acoustics and Speech Communication, Dresden University of Technology, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Dresden University of Technology, Laboratory of Acoustics and Speech Communication, D-01062, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021607001"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":1.4203,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82326478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9977999925613403,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.8500053882598877},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.828399658203125},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8175668120384216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8067126274108887},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7009621858596802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6243360042572021},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6194359660148621},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5671775341033936},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45614147186279297},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.420917809009552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39146023988723755},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3589620292186737},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09579771757125854}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8500053882598877},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.828399658203125},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8175668120384216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067126274108887},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7009621858596802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6243360042572021},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6194359660148621},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5671775341033936},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45614147186279297},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.420917809009552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39146023988723755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3589620292186737},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09579771757125854},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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.2002.5743743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743743","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W38355094","https://openalex.org/W181732614","https://openalex.org/W202137502","https://openalex.org/W1481576417","https://openalex.org/W1849971598","https://openalex.org/W1882466690","https://openalex.org/W1927439458","https://openalex.org/W2066452495","https://openalex.org/W2122598882","https://openalex.org/W2985376554","https://openalex.org/W6607394350","https://openalex.org/W6608202415","https://openalex.org/W6639154810"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W15468680"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,47],"systems":[2],"based":[3],"on":[4,70],"concatenation":[5],"of":[6,52],"segments":[7],"derived":[8],"from":[9],"natural":[10],"speech":[11,46],"are":[12,76,85],"very":[13,77],"intelligible":[14],"and":[15,32,89,111],"achieve":[16],"a":[17,39,53,82,107],"high":[18],"overall":[19],"quality.":[20],"Even":[21],"though":[22],"listeners":[23],"often":[24],"complain":[25],"about":[26],"wrong":[27],"or":[28],"missing":[29],"temporal":[30],"structure":[31],"timing":[33],"in":[34,45,55,81],"synthetic":[35],"speech.":[36],"We":[37],"propose":[38],"new":[40],"approach":[41],"for":[42],"duration":[43,104],"control":[44,59,105],"that":[48,73,75,101],"uses":[49],"the":[50,60,65,71,103],"probability":[51],"word":[54],"its":[56],"context":[57,84],"to":[58,79],"local":[61],"speaking":[62],"rate":[63],"within":[64],"utterance.":[66],"This":[67],"idea":[68],"bases":[69],"observation":[72],"words":[74],"likely":[78],"occur":[80],"given":[83],"pronounced":[86],"less":[87],"accurate":[88],"faster":[90],"than":[91],"improbable":[92],"ones.":[93],"In":[94],"this":[95],"paper":[96],"we":[97],"introduce":[98],"an":[99],"algorithm":[100],"implements":[102],"using":[106],"multigram":[108],"language":[109],"model":[110],"will":[112],"present":[113],"first":[114],"experimental":[115],"results.":[116]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
