{"id":"https://openalex.org/W64921504","doi":"https://doi.org/10.21437/interspeech.2008-178","title":"Structure to speech conversion - speech generation based on infant-like vocal imitation","display_name":"Structure to speech conversion - speech generation based on infant-like vocal imitation","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W64921504","doi":"https://doi.org/10.21437/interspeech.2008-178","mag":"64921504"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-178","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103581782","display_name":"Satoshi Asakawa","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":"Satoshi Asakawa","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"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":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","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":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1837","last_page":"1840"},"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":0.9976999759674072,"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":0.9955999851226807,"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/imitation","display_name":"Imitation","score":0.8507829904556274},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.790852427482605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7324225306510925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6471303701400757},{"id":"https://openalex.org/keywords/gestalt-psychology","display_name":"Gestalt psychology","score":0.5747136473655701},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5078650116920471},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4699343144893646},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.43742966651916504},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4136224091053009},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33883535861968994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3262154459953308},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27715936303138733},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2544516324996948}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.8507829904556274},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.790852427482605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7324225306510925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471303701400757},{"id":"https://openalex.org/C27362006","wikidata":"https://www.wikidata.org/wiki/Q272021","display_name":"Gestalt psychology","level":3,"score":0.5747136473655701},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5078650116920471},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4699343144893646},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.43742966651916504},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4136224091053009},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33883535861968994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262154459953308},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27715936303138733},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2544516324996948},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2008-178","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.3822","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.3822","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/2008/INTERSPEECH_p1837-1840_t2008-9.PDF","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W204204962","https://openalex.org/W2049686551","https://openalex.org/W2100012411","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":[0,114],"paper":[1],"proposes":[2],"a":[3,21,36,44,74,78,131,151,166],"new":[4],"framework":[5],"of":[6,16,32,47,80,95,100,133,153],"speech":[7,18,28,55,160,178],"generation":[8,56],"by":[9,29],"imitating":[10],"\u201cinfants":[11],"\u2019":[12,173],"vocal":[13,112,118,174,180],"imitation\u201d.":[14],"Most":[15],"the":[17,33,91,98,124,155],"synthe-sizers":[19],"take":[20],"phoneme":[22,61],"sequence":[23,79],"as":[24,85],"input":[25],"and":[26,106,130,141,146,163],"generate":[27],"converting":[30,154],"each":[31],"phonemes":[34],"into":[35,77],"sound":[37,93],"sequentially.":[38],"In":[39,82,120,148],"other":[40],"words,":[41],"they":[42,70,107],"simulate":[43],"human":[45],"process":[46],"reading":[48],"text":[49,59],"out.":[50],"However,":[51],"infants":[52,89,172],"usually":[53],"acquire":[54,90],"abil-ity":[57],"without":[58],"or":[60],"sequences.":[62],"Since":[63],"their":[64,101,111],"phonemic":[65],"awareness":[66],"is":[67,116,161],"very":[68],"immature,":[69],"can":[71],"hardly":[72],"decompose":[73],"word":[75,104,125,156,182],"utterance":[76,138],"phones.":[81],"this":[83,149],"situation,":[84],"devel-opmental":[86],"psychology":[87],"states,":[88],"holistic":[92],"pattern":[94],"words":[96],"from":[97,136],"utterances":[99],"parents,":[102],"called":[103,117],"Gestalt,":[105,183],"reproduce":[108],"it":[109,135],"with":[110],"tubes.":[113],"behavior":[115],"imitation.":[119,175],"our":[121,169],"previous":[122],"studies,":[123],"Gestalt":[126,157],"was":[127,139],"defined":[128],"physically":[129],"method":[132,152],"extract-ing":[134],"an":[137],"proposed":[140,162],"used":[142],"successfully":[143],"for":[144],"ASR":[145],"CALL.":[147],"paper,":[150],"back":[158],"to":[159],"evaluated.":[164],"Unlike":[165],"read-ing":[167],"machine,":[168],"proposal":[170],"simulates":[171],"Index":[176],"Terms:":[177],"synthesis,":[179],"imitation,":[181],"invariant":[184],"structure,":[185],"Bhattacharyya":[186],"distance,":[187],"searching":[188],"problem":[189]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}