{"id":"https://openalex.org/W2404126548","doi":"https://doi.org/10.21437/icslp.1992-277","title":"The design for the wall street journal-based CSR corpus","display_name":"The design for the wall street journal-based CSR corpus","publication_year":1992,"publication_date":"1992-10-13","ids":{"openalex":"https://openalex.org/W2404126548","doi":"https://doi.org/10.21437/icslp.1992-277","mag":"2404126548"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1992-277","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1992-277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2nd International Conference on Spoken Language Processing (ICSLP 1992)","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/A5109968442","display_name":"Douglas B. Paul","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Douglas B. Paul","raw_affiliation_strings":["Lincoln Laboratory, MIT, Lexington, Ma.#TAB#"],"affiliations":[{"raw_affiliation_string":"Lincoln Laboratory, MIT, Lexington, Ma.#TAB#","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101529371","display_name":"Janet M. Baker","orcid":"https://orcid.org/0000-0002-1058-7402"},"institutions":[{"id":"https://openalex.org/I4210086460","display_name":"Wave Dragon (Denmark)","ror":"https://ror.org/001y71q13","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210086460"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Janet M. Baker","raw_affiliation_strings":["Dragon Systems, Inc., Newton, Ma.#TAB#"],"affiliations":[{"raw_affiliation_string":"Dragon Systems, Inc., Newton, Ma.#TAB#","institution_ids":["https://openalex.org/I4210086460"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109968442"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":2.775,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.9142807,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"899","last_page":"902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9927999973297119,"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":0.9927999973297119,"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":0.9402999877929688,"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":0.914900004863739,"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/perplexity","display_name":"Perplexity","score":0.9420773983001709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7810884714126587},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6696817874908447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796414017677307},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5439029932022095},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5412504076957703},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.5140267610549927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3696472644805908},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.30646342039108276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2514076828956604}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9420773983001709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810884714126587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6696817874908447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796414017677307},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5439029932022095},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5412504076957703},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.5140267610549927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3696472644805908},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30646342039108276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2514076828956604},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.21437/icslp.1992-277","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1992-277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2nd International Conference on Spoken Language Processing (ICSLP 1992)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"The":[0,29],"DARPA":[1,58],"Spoken":[2],"Language":[3],"System":[4],"(SLS)":[5],"community":[6],"has":[7],"long":[8],"taken":[9],"a":[10,86],"leadership":[11],"position":[12],"in":[13,96],"designing,":[14],"implementing,":[15],"and":[16,79,92,117],"globally":[17],"distributing":[18],"significant":[19,71],"speech":[20,26,75,90],"corpora":[21],"widely":[22],"used":[23],"for":[24],"advancing":[25],"recognition":[27,91],"research.":[28],"Wall":[30],"Street":[31],"Journal":[32],"(WSJ)":[33],"CSR":[34,125],"Corpus":[35],"described":[36],"here":[37],"is":[38],"the":[39,53,107,122],"newest":[40],"addition":[41],"to":[42,50,88],"this":[43],"valuable":[44],"set":[45],"of":[46,73],"resources.":[47],"In":[48],"contrast":[49],"previous":[51],"corpora,":[52],"WSJ":[54,124],"corpus":[55,69],"will":[56],"provide":[57],"its":[59],"first":[60],"general-purpose":[61],"English,":[62],"large":[63],"vocabulary,":[64],"natural":[65,93],"language,":[66],"high":[67,100],"perplexity,":[68],"containing":[70],"quantities":[72],"both":[74],"data":[76,81,111],"(400":[77],"hrs.)":[78],"text":[80,113],"(47M":[82],"words),":[83],"thereby":[84],"providing":[85],"means":[87],"integrate":[89],"language":[94],"processing":[95,114],"application":[97],"domains":[98],"with":[99],"potential":[101],"practical":[102],"value.":[103],"This":[104],"paper":[105],"presents":[106],"motivating":[108],"goals,":[109],"acoustic":[110],"design,":[112],"steps,":[115],"lexicons,":[116],"testing":[118],"paradigms":[119],"incorporated":[120],"into":[121],"multi-faceted":[123],"Corpus.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}