{"id":"https://openalex.org/W2157092853","doi":"https://doi.org/10.1109/cbmi.2008.4564941","title":"Automatic correspondence calculation between text and speech for authoring digital talking book","display_name":"Automatic correspondence calculation between text and speech for authoring digital talking book","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2157092853","doi":"https://doi.org/10.1109/cbmi.2008.4564941","mag":"2157092853"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi.2008.4564941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2008.4564941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Workshop on Content-Based Multimedia Indexing","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/A5045117437","display_name":"Katsuyuki Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuyuki Watanabe","raw_affiliation_strings":["Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103479846","display_name":"Masahide Sugiyama","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahide Sugiyama","raw_affiliation_strings":["Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11735767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"155","last_page":"161"},"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8001450300216675},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7368605732917786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7182210683822632},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4728061258792877},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4413999915122986},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4141640067100525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4041305184364319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001450300216675},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7368605732917786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7182210683822632},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4728061258792877},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4141640067100525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041305184364319},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi.2008.4564941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2008.4564941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Workshop on Content-Based Multimedia Indexing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W210770835","https://openalex.org/W1772620444","https://openalex.org/W1987312571","https://openalex.org/W2010021469","https://openalex.org/W2133059825","https://openalex.org/W2148154194","https://openalex.org/W2164282073","https://openalex.org/W2168119002","https://openalex.org/W2916092813","https://openalex.org/W3049369830","https://openalex.org/W6608545824","https://openalex.org/W6637936407"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2375873920","https://openalex.org/W2349768204","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W4313326281","https://openalex.org/W2009831055","https://openalex.org/W2393172683"],"abstract_inverted_index":{"The":[0,19,117,145],"present":[1,84],"paper":[2],"proposes":[3],"applying":[4],"the":[5,27,37,42,57,61,65,83,86,94,99,122,131],"voice-pause":[6],"(VP)":[7],"method":[8,21,89,148],"to":[9,24,45,69,76,92],"authoring":[10],"DAISY":[11],"talking":[12],"books":[13],"used":[14,91],"by":[15],"visually":[16],"impaired":[17],"people.":[18],"proposed":[20,87,146,157],"enables":[22],"authors":[23],"automatically":[25],"calculate":[26,56],"time":[28,43,58,97,125],"information":[29,59],"of":[30,60,142],"sentence-based":[31],"correspondence":[32],"between":[33],"Japanese":[34],"text":[35],"and":[36,75,98,109,130,138,151],"corresponding":[38],"audio":[39,67,112],"data,":[40],"reducing":[41],"required":[44],"perform":[46],"searches.":[47],"While":[48],"there":[49],"have":[50,70],"been":[51],"several":[52],"related":[53],"studies":[54],"that":[55,121],"correspondence,":[62],"they":[63],"require":[64],"input":[66,111],"data":[68,113],"a":[71],"specific":[72],"speech":[73,107,143],"style":[74],"be":[77],"short":[78],"in":[79,82,158],"duration.":[80],"Therefore,":[81],"paper,":[85],"VP":[88,147],"was":[90,126,135],"determine":[93],"average":[95,123],"gap":[96,124],"sentence":[100,132],"detection":[101,133],"rate":[102,134],"for":[103,110],"databases":[104],"having":[105,114],"different":[106],"styles":[108],"long":[115],"durations.":[116],"experimental":[118],"results":[119],"show":[120],"approximately":[127,136],"0.38":[128],"sec":[129],"94%":[137],"these":[139],"are":[140],"independent":[141],"style.":[144],"performs":[149],"well":[150],"is":[152],"efficient":[153],"compared":[154],"with":[155],"methods":[156],"previous":[159],"studies.":[160]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}