{"id":"https://openalex.org/W322416068","doi":"https://doi.org/10.21437/interspeech.2009-588","title":"Optimal event search using a structural cost function - improvement of structure to speech conversion","display_name":"Optimal event search using a structural cost function - improvement of structure to speech conversion","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W322416068","doi":"https://doi.org/10.21437/interspeech.2009-588","mag":"322416068"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-588","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2047","last_page":"2050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9896000027656555,"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/utterance","display_name":"Utterance","score":0.7904995679855347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617254257202148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7348959445953369},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6695300340652466},{"id":"https://openalex.org/keywords/gestalt-psychology","display_name":"Gestalt psychology","score":0.5790436267852783},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5443021059036255},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44768738746643066},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4445624351501465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4324643015861511},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.432273805141449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40031591057777405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20703774690628052},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12045729160308838}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7904995679855347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617254257202148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7348959445953369},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6695300340652466},{"id":"https://openalex.org/C27362006","wikidata":"https://www.wikidata.org/wiki/Q272021","display_name":"Gestalt psychology","level":3,"score":0.5790436267852783},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5443021059036255},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44768738746643066},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4445624351501465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4324643015861511},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.432273805141449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40031591057777405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20703774690628052},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12045729160308838},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-588","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.7684","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.7684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2009/INTERSPEECH_p2047-2050_t2009-9.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W15693373","https://openalex.org/W64921504","https://openalex.org/W204204962","https://openalex.org/W2049686551","https://openalex.org/W2114492809","https://openalex.org/W2115606020","https://openalex.org/W2168862296"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W1593175091"],"abstract_inverted_index":{"This":[0,116],"paper":[1],"describes":[2],"a":[3,25,48,81,133,139,177,187,204],"new":[4],"and":[5,30,108,132,153,193],"improved":[6],"method":[7,134,178],"for":[8,179],"the":[9,21,37,93,100,126,147,199],"frame-work":[10],"of":[11,20,36,51,83,97,102,135],"structure":[12,160],"to":[13,150,161],"speech":[14,22,32,59,155,162,182,197],"conversion":[15],"we":[16,158],"previously":[17],"proposed.":[18,143],"Most":[19],"synthesizers":[23],"take":[24],"phoneme":[26,65],"sequence":[27,82],"as":[28],"input":[29],"generate":[31],"by":[33],"converting":[34],"each":[35],"phonemes":[38],"into":[39,80],"its":[40],"corresponding":[41],"sound.":[42],"In":[43,122,174],"other":[44],"words,":[45],"they":[46,74,109],"simulate":[47],"human":[49],"process":[50],"reading":[52,165],"text":[53,63],"out.":[54],"However,":[55],"infants":[56,170],"usually":[57],"acquire":[58,92],"communication":[60],"ability":[61],"without":[62],"or":[64,85],"sequences.":[66],"Since":[67],"their":[68,103,113],"phonemic":[69],"awareness":[70],"is":[71,118,191],"very":[72],"immature,":[73],"can":[75],"hardly":[76],"decompose":[77],"an":[78],"utterance":[79,141],"phones":[84],"phonemes.":[86],"As":[87],"developmental":[88],"psychology":[89],"claims,":[90],"in-fants":[91],"holistic":[94],"sound":[95],"patterns":[96],"words":[98],"from":[99,138],"utter-ances":[101],"parents,":[104],"called":[105,119],"word":[106,127,140,148],"Gestalt,":[107],"reproduce":[110],"them":[111],"with":[112],"vocal":[114,120,172,202],"tubes.":[115],"behavior":[117],"im-itation.":[121],"our":[123,167,181],"previous":[124],"studies,":[125],"Gestalt":[128,149],"was":[129,142],"defined":[130],"physically":[131],"extracting":[136],"it":[137],"We":[144],"already":[145],"applied":[146],"ASR,":[151],"CALL,":[152],"also":[154],"generation,":[156],"which":[157],"call":[159],"conversion.":[163],"Unlike":[164],"machines,":[166],"framework":[168,184],"simulates":[169],"\u2019":[171],"imitation.":[173],"this":[175],"paper,":[176],"improving":[180],"generation":[183],"based":[185],"on":[186],"struc-tural":[188],"cost":[189,206],"function":[190,207],"proposed":[192],"evaluated.":[194],"Index":[195],"Terms:":[196],"synthesis,":[198],"structural":[200,205],"representation,":[201],"imitation,":[203]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
