{"id":"https://openalex.org/W111396543","doi":"https://doi.org/10.21437/interspeech.2005-604","title":"Duration modeling and memory optimization in a Mandarin TTS system","display_name":"Duration modeling and memory optimization in a Mandarin TTS system","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W111396543","doi":"https://doi.org/10.21437/interspeech.2005-604","mag":"111396543"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-604","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5103093321","display_name":"Jilei Tian","orcid":"https://orcid.org/0000-0002-4588-9398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jilei Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112039585","display_name":"Jani Nurminen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jani Nurminen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040670032","display_name":"Imre Kiss","orcid":"https://orcid.org/0000-0001-5373-7485"},"institutions":[{"id":"https://openalex.org/I4210106018","display_name":"Nokia (Netherlands)","ror":"https://ror.org/01resg468","country_code":"NL","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210106018"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Imre Kiss","raw_affiliation_strings":["Nokia,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia,#TAB#","institution_ids":["https://openalex.org/I4210106018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2465,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44280931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1929","last_page":"1932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9900000095367432,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9883000254631042,"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/computer-science","display_name":"Computer science","score":0.8078517913818359},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7980390787124634},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6735484600067139},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6492177248001099},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.638177752494812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6064572334289551},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5860896110534668},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5701590776443481},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.518064022064209},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5003573894500732},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3552906811237335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3502447009086609},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14889395236968994},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09656038880348206},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07861307263374329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078517913818359},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7980390787124634},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6735484600067139},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6492177248001099},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.638177752494812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6064572334289551},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5860896110534668},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5701590776443481},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.518064022064209},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5003573894500732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3552906811237335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3502447009086609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14889395236968994},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09656038880348206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07861307263374329},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-604","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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":4,"referenced_works":["https://openalex.org/W1510007267","https://openalex.org/W1578856370","https://openalex.org/W1955848339","https://openalex.org/W2108363342"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W234770729","https://openalex.org/W4391272374","https://openalex.org/W4400309480","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Current":[0],"speech":[1,53,120,147],"synthesis":[2,148],"efforts,":[3],"both":[4],"in":[5,8,22,55,72,99,145],"research":[6],"and":[7,59,89,111],"applications,":[9],"are":[10,65],"dominated":[11],"by":[12,36,49],"methods":[13],"based":[14],"on":[15,67],"concatenation":[16],"of":[17,57,92,107,140],"spoken":[18],"units.":[19],"New":[20],"progress":[21],"the":[23,38,43,51,68,93,100,104,108,119,141,146],"concatenative":[24],"text-to-speech":[25],"(TTS)":[26],"technology":[27],"can":[28,83,113],"be":[29,84,114],"made":[30],"mainly":[31],"from":[32],"two":[33],"directions,":[34],"either":[35],"reducing":[37],"memory":[39,69,81,90,105],"footprint":[40,70],"to":[41],"integrate":[42],"system":[44],"into":[45],"embedded":[46,125],"system,":[47],"or":[48],"improving":[50],"synthesized":[52],"quality":[54,121],"terms":[56],"intelligibility":[58],"naturalness.":[60],"In":[61],"this":[62,127],"paper,":[63],"we":[64],"focusing":[66],"reduction":[71],"a":[73,129],"Mandarin":[74],"TTS":[75,135],"system.":[76,149],"We":[77],"show":[78],"that":[79,103],"significant":[80,130],"reductions":[82],"achieved":[85],"through":[86],"duration":[87,109],"modeling":[88],"optimization":[91],"lexicon":[94,112],"data.":[95],"The":[96,138],"results":[97],"obtained":[98],"experiments":[101],"indicate":[102],"requirements":[106],"data":[110],"significantly":[115],"reduced":[116],"while":[117],"keeping":[118],"unaffected.":[122],"For":[123],"practical":[124],"implementations,":[126],"is":[128,143],"step":[131],"towards":[132],"an":[133],"efficient":[134],"engine":[136],"implementation.":[137],"applicability":[139],"approach":[142],"verified":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}