{"id":"https://openalex.org/W2107457864","doi":"https://doi.org/10.1109/icme.2011.6012185","title":"Automatic synchronization of electronic and audio books via TTS alignment and silence filtering","display_name":"Automatic synchronization of electronic and audio books via TTS alignment and silence filtering","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2107457864","doi":"https://doi.org/10.1109/icme.2011.6012185","mag":"2107457864"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2011.6012185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2011.6012185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Multimedia and Expo","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/A5051383020","display_name":"Xavier Anguera","orcid":"https://orcid.org/0000-0001-8659-3991"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Xavier Anguera","raw_affiliation_strings":["Telefonica Research and Development, Barcelona, Spain","Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research and Development, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111185127","display_name":"N. P\u00e9rez","orcid":"https://orcid.org/0009-0007-0002-9785"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nestor Perez","raw_affiliation_strings":["Telefonica Research and Development, Barcelona, Spain","Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research and Development, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088467040","display_name":"A. Urruela","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andreu Urruela","raw_affiliation_strings":["Telefonica Research and Development, Barcelona, Spain","Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research and Development, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013727792","display_name":"Nuria Oliver","orcid":"https://orcid.org/0000-0001-5985-691X"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nuria Oliver","raw_affiliation_strings":["Telefonica Research and Development, Barcelona, Spain","Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Telefonica Research and Development, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research, Torre Telefonica Diagonal 00, 08019, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051383020"],"corresponding_institution_ids":["https://openalex.org/I4210134591"],"apc_list":null,"apc_paid":null,"fwci":1.2478,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80096298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reading","display_name":"Reading (process)","score":0.7951892614364624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7883313894271851},{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.7354359030723572},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7179772257804871},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6542848944664001},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5993633270263672},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5658498406410217},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.564588725566864},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.538110077381134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.504067063331604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18639826774597168},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1475212275981903},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08109000325202942},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07145020365715027}],"concepts":[{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.7951892614364624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883313894271851},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.7354359030723572},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7179772257804871},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6542848944664001},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5993633270263672},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5658498406410217},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.564588725566864},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.538110077381134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.504067063331604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18639826774597168},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1475212275981903},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08109000325202942},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07145020365715027},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2011.6012185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2011.6012185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.654.6820","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.654.6820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.xavieranguera.com/papers/icme2011b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W1510837697","https://openalex.org/W1521159288","https://openalex.org/W1527232260","https://openalex.org/W1553635428","https://openalex.org/W1965794551","https://openalex.org/W2033037901","https://openalex.org/W2085797365","https://openalex.org/W2128160875","https://openalex.org/W2130890537","https://openalex.org/W2149062204","https://openalex.org/W2170980774","https://openalex.org/W2331071225","https://openalex.org/W2791177604","https://openalex.org/W6600436803","https://openalex.org/W6630406810","https://openalex.org/W6633070098"],"related_works":["https://openalex.org/W2140535326","https://openalex.org/W1607271848","https://openalex.org/W4251121070","https://openalex.org/W2734809835","https://openalex.org/W2184961913","https://openalex.org/W1965764303","https://openalex.org/W2750153830","https://openalex.org/W2214987084","https://openalex.org/W1964726586","https://openalex.org/W3008391423"],"abstract_inverted_index":{"The":[0],"e-book":[1,17,174],"industry":[2],"is":[3,31],"starting":[4],"to":[5,10,28,34,53,85,103,115,178],"flourish":[6],"due,":[7],"in":[8,51,130,169],"part,":[9],"the":[11,45,55,70,73,86,118,124,128,131,159,170,179],"availability":[12],"of":[13,48,57,72,140,158],"affordable":[14],"and":[15,36,107,127,147],"user-friendly":[16],"readers.":[18],"As":[19],"users":[20,82],"are":[21,89],"increasingly":[22],"moving":[23],"from":[24],"traditional":[25],"paper":[26],"books":[27],"e-books,":[29],"there":[30],"an":[32,94],"opportunity":[33],"reinvent":[35],"enhance":[37,108],"their":[38],"reading":[39,58,121,175],"experience,":[40],"for":[41,156,172],"example,":[42],"by":[43,98,145],"leveraging":[44],"multimedia":[46,62],"capabilities":[47],"these":[49],"devices":[50],"order":[52],"turn":[54],"act":[56],"into":[59],"a":[60,100,111,165],"real":[61],"experience.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,162],"focus":[68],"on":[69,120],"augmentation":[71],"written":[74],"text":[75,102],"with":[76,110,117],"its":[77],"associated":[78,180],"audiobook,":[79],"so":[80],"that":[81],"can":[83],"listen":[84],"book":[87],"they":[88],"(currently)":[90],"reading.":[91],"We":[92],"propose":[93],"audiobook-to-ebook":[95],"alignment":[96,105,152],"system":[97],"applying":[99],"Text-to-Speech(TTS)-based":[101],"audio":[104],"algorithm,":[106],"it":[109],"silence":[112],"filtering":[113],"algorithm":[114],"cope":[116],"difference":[119],"style":[122],"between":[123],"TTS":[125],"output":[126],"speakers":[129],"ebook":[132],"environment.":[133],"Experiments":[134],"done":[135],"using":[136],"12":[137],"five-minute":[138],"excerpts":[139],"6":[141],"different":[142],"audio-books":[143],"(read":[144],"men":[146],"women)":[148],"yield":[149],"usable":[150],"word":[151],"errors":[153],"below":[154],"120ms":[155],"90%":[157],"words.":[160],"Finally,":[161],"also":[163],"show":[164],"user":[166],"interface":[167],"implementation":[168],"Ipad":[171],"synchronized":[173],"while":[176],"listening":[177],"audiobook.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
