{"id":"https://openalex.org/W2107755572","doi":"https://doi.org/10.21437/eurospeech.2003-331","title":"Automated transcription and topic segmentation of large spoken archives","display_name":"Automated transcription and topic segmentation of large spoken archives","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2107755572","doi":"https://doi.org/10.21437/eurospeech.2003-331","mag":"2107755572"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-331","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5071900309","display_name":"Martin Franz","orcid":"https://orcid.org/0000-0001-6697-3022"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Martin Franz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111895145","display_name":"Todd Ward","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Todd Ward","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071900309"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5686,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94769775,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"953","last_page":"956"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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":0.9941999912261963,"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":0.8037747740745544},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.6961919069290161},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5784246921539307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5098509192466736},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48522472381591797},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45799264311790466},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.44840574264526367},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41774508357048035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4123397171497345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3923502564430237},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3243752121925354},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21102595329284668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037747740745544},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.6961919069290161},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5784246921539307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5098509192466736},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48522472381591797},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45799264311790466},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.44840574264526367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41774508357048035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4123397171497345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3923502564430237},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3243752121925354},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21102595329284668},{"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:10.21437/eurospeech.2003-331","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1496393218","https://openalex.org/W1522951677","https://openalex.org/W1525467807","https://openalex.org/W1977986156","https://openalex.org/W2103584254"],"related_works":["https://openalex.org/W2791807133","https://openalex.org/W1009706782","https://openalex.org/W2141266967","https://openalex.org/W2765804957","https://openalex.org/W2962716343","https://openalex.org/W43702919","https://openalex.org/W845924147","https://openalex.org/W2096389830","https://openalex.org/W2060410964","https://openalex.org/W1499383998"],"abstract_inverted_index":{"Digital":[0],"archives":[1,15,29,98],"have":[2,57,159],"emerged":[3],"as":[4],"the":[5,10,32,67,78,81,93,101,163,167,179],"pre-eminent":[6],"method":[7],"for":[8,51,162],"capturing":[9],"human":[11],"experience.":[12],"Before":[13],"such":[14,28,97],"can":[16],"be":[17,23],"used":[18],"efficiently,":[19],"their":[20],"contents":[21],"must":[22],"described.":[24],"The":[25,61],"scale":[26],"of":[27,72,80,120,124,151,182],"along":[30],"with":[31,136],"associated":[33],"content":[34],"mark":[35],"up":[36],"cost":[37],"make":[38,88],"it":[39],"impractical":[40],"to":[41,87,95],"provide":[42],"access":[43,96],"via":[44],"purely":[45],"manual":[46],"means,":[47],"but":[48],"automatic":[49],"technologies":[50,114,156],"search":[52],"in":[53,92,103,131,166],"spoken":[54],"materials":[55],"still":[56],"relatively":[58],"limited":[59],"capabilities.":[60],"NSF-funded":[62],"MALACH":[63,168],"project":[64],"will":[65],"use":[66],"world\u2019s":[68],"largest":[69],"digital":[70],"archive":[71],"video":[73],"oral":[74],"histories,":[75],"collected":[76],"by":[77,99],"Survivors":[79],"Shoah":[82],"Visual":[83],"History":[84],"Foundation":[85],"(VHF)":[86],"a":[89],"quantum":[90],"leap":[91],"ability":[94],"advancing":[100],"state-of-the-art":[102],"Automated":[104],"Speech":[105],"Recognition":[106],"(ASR),":[107],"Natural":[108],"Language":[109],"Processing":[110],"(NLP)":[111],"and":[112,142,145,153,155],"related":[113],"[1,":[115],"2].":[116],"This":[117],"corpus":[118],"consists":[119],"over":[121],"115,000":[122],"hours":[123],"unconstrained,":[125],"natural":[126],"speech":[127,165],"from":[128],"52,000":[129],"speakers":[130],"32":[132],"different":[133],"languages,":[134],"filled":[135],"disfluencies,":[137],"heavy":[138],"accents,":[139],"age-related":[140],"coarticulations,":[141],"un-cued":[143],"speaker":[144],"language":[146],"switching.":[147],"Thispaper":[148],"discusses":[149],"some":[150],"theASR":[152],"NLPtools":[154],"that":[157],"we":[158],"been":[160],"building":[161],"English":[164],"corpus.":[169,184],"We":[170],"also":[171],"discuss":[172],"this":[173,183],"new":[174],"test":[175],"bed":[176],"while":[177],"emphasizing":[178],"unique":[180],"characteristics":[181]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}