{"id":"https://openalex.org/W2085494764","doi":"https://doi.org/10.1145/2390116.2390130","title":"Need for automatically generated narration","display_name":"Need for automatically generated narration","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2085494764","doi":"https://doi.org/10.1145/2390116.2390130","mag":"2085494764"},"language":"en","primary_location":{"id":"doi:10.1145/2390116.2390130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2390116.2390130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM workshop on Research advances in large digital book repositories and complementary media","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/A5049350495","display_name":"David A. Evans","orcid":"https://orcid.org/0000-0002-8964-9169"},"institutions":[{"id":"https://openalex.org/I4210129820","display_name":"Evans Analytical Group (United States)","ror":"https://ror.org/03f0b2d64","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Evans","raw_affiliation_strings":["David A Evans LLC, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"David A Evans LLC, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210129820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061455081","display_name":"John Reichenbach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Reichenbach","raw_affiliation_strings":["Lessac Technologies, West Newton, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lessac Technologies, West Newton, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4954,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68045279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7408218383789062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7371803522109985},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.7271745204925537},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.7237119674682617},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6428970098495483},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5821878910064697},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5365991592407227},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5070085525512695},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.48683494329452515},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34332841634750366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.28459447622299194},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22908049821853638},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11111634969711304},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.11020424962043762},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08773943781852722},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07390406727790833}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7408218383789062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371803522109985},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.7271745204925537},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.7237119674682617},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6428970098495483},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5821878910064697},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5365991592407227},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5070085525512695},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.48683494329452515},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34332841634750366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28459447622299194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22908049821853638},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11111634969711304},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.11020424962043762},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08773943781852722},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07390406727790833},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":1,"locations":[{"id":"doi:10.1145/2390116.2390130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2390116.2390130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM workshop on Research advances in large digital book repositories and complementary media","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1994869569","https://openalex.org/W2093696618","https://openalex.org/W2143827132","https://openalex.org/W2172102321","https://openalex.org/W2188668519","https://openalex.org/W2330075180","https://openalex.org/W2553602441","https://openalex.org/W3137346669"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"This":[0,131],"paper":[1],"argues":[2],"that":[3,51],"the":[4,13,57,70,137],"best":[5],"current":[6],"text-to-speech":[7],"(TTS)":[8],"synthesis":[9],"systems":[10,88],"are":[11,32,63],"approaching":[12],"quality":[14,97],"necessary":[15],"to":[16,98,101,119,148,150],"provide":[17],"effective":[18],"automated":[19],"narration":[20],"of":[21,56,75,95,127],"audio":[22,27,30],"books.":[23],"Currently,":[24],"nearly":[25],"all":[26],"books":[28],"and":[29,47,72,107,114,145],"journals":[31],"recorded":[33],"by":[34],"professional":[35],"voice":[36,93],"actors":[37],"at":[38],"great":[39],"expense":[40],"with":[41,77],"significant":[42],"lead":[43],"times.":[44],"These":[45],"cost":[46],"time":[48,118],"constraints":[49],"mean":[50],"fewer":[52],"than":[53,54],"2%":[55],"new":[58],"titles":[59],"published":[60],"each":[61],"year":[62],"available":[64],"in":[65,83],"\"Talking":[66],"Book\"":[67],"editions,":[68],"leaving":[69],"visually-impaired":[71],"print-disabled":[73],"community":[74],"users":[76,147],"few":[78],"options":[79],"when":[80],"seeking":[81],"material":[82],"digital":[84,129],"libraries.":[85],"State-of-the-art":[86],"TTS":[87],"now":[89],"can":[90],"reproduce":[91],"human":[92],"prosody":[94],"sufficient":[96],"make":[99],"listening":[100],"long":[102],"narrative":[103],"reading":[104,156],"both":[105],"pleasant":[106],"comprehensible.":[108],"Such":[109],"technology":[110],"is":[111,117],"relatively":[112],"compact":[113],"inexpensive;":[115],"it":[116,121],"deploy":[120],"widely":[122],"as":[123],"an":[124],"alternative":[125],"means":[126],"accessing":[128],"texts.":[130],"would":[132],"not":[133,158],"only":[134],"directly":[135],"benefit":[136],"reading-disabled":[138],"community,":[139],"but":[140],"also":[141],"enable":[142],"\"digital":[143],"natives\"":[144],"other":[146],"listen":[149],"texts":[151],"on":[152,154],"platforms":[153],"which":[155],"may":[157],"be":[159],"practical.":[160]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
