{"id":"https://openalex.org/W108207029","doi":"https://doi.org/10.21437/icslp.1998-630","title":"Fabricating conversational speech data with acoustic models: a program to examine model-data mismatch","display_name":"Fabricating conversational speech data with acoustic models: a program to examine model-data mismatch","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W108207029","doi":"https://doi.org/10.21437/icslp.1998-630","mag":"108207029"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-630","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5056421223","display_name":"Don McAllaster","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Don McAllaster","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027543842","display_name":"Lawrence Gillick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lawrence Gillick","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018681993","display_name":"Francesco Scattone","orcid":"https://orcid.org/0000-0002-7656-8167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Scattone","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011226138","display_name":"Michael Newman","orcid":"https://orcid.org/0000-0002-8581-3152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Newman","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056421223"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3526,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.95511014,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"paper 0986","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.993399977684021,"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":0.993399977684021,"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":0.9560999870300293,"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":0.9553999900817871,"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":0.7986264228820801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7677662372589111},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6888936758041382},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6847246885299683},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6591452956199646},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5693165063858032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45523810386657715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42941534519195557},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3853439688682556},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0920005738735199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986264228820801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7677662372589111},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6888936758041382},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6847246885299683},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6591452956199646},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5693165063858032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45523810386657715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42941534519195557},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3853439688682556},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0920005738735199},{"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.1998-630","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W196692374","https://openalex.org/W2120699805"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W4385611764"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,32,68,75,115,130,157,177],"study":[3],"of":[4,37,51,70,78,139,152,169],"data":[5,47,87],"simulated":[6],"using":[7,17,48],"acoustic":[8,20,141],"models":[9,30,142],"trained":[10],"on":[11],"Switchboard":[12,26],"data,":[13],"and":[14,94,118,136,143,165,172],"then":[15],"recognized":[16],"various":[18],"Switchboard-trained":[19],"models.":[21],"When":[22],"we":[23,43,80,121],"recognize":[24],"real":[25,134],"conversations,":[27],"simple":[28],"development":[29],"give":[31],"word":[33,49],"error":[34],"rate":[35],"(WER)":[36],"about":[38],"47":[39],"percent.":[40],"If":[41],"instead":[42],"simulate":[44],"the":[45,52,55,58,64,98,124,137,144,167],"speech":[46,111,135,182],"transcriptions":[50],"conversation,":[53],"obtaining":[54],"pronunciations":[56,145],"for":[57],"words":[59],"from":[60],"our":[61,140,147,161],"recognition":[62,148,183],"dictionary,":[63],"WER":[65],"drops":[66],"by":[67],"factor":[69],"five":[71],"to":[72,85,106,155,163,175],"ten.":[73],"In":[74],"third":[76],"type":[77],"experiment,":[79],"use":[81,151],"human-generated":[82],"phonetic":[83],"transcripts":[84],"fabricate":[86],"that":[88,102,127],"more":[89],"realistically":[90],"represents":[91],"conversational":[92],"speech,":[93],"obtain":[95],"WERs":[96],"in":[97,109,123,146,160,181],"low":[99],"40\u2019s,":[100],"rates":[101],"are":[103],"fairly":[104],"similar":[105],"those":[107],"seen":[108],"actual":[110],"data.":[112],"Taken":[113],"as":[114],"whole,":[116],"these":[117],"other":[119],"experiments":[120],"describe":[122],"paper":[125],"suggest":[126],"there":[128],"is":[129],"substantial":[131],"mismatch":[132],"between":[133],"combination":[138],"dictionary.":[149],"The":[150],"simulation":[153],"appears":[154],"be":[156,176],"promising":[158],"tool":[159],"efforts":[162],"understand":[164],"reduce":[166],"size":[168],"this":[170],"mismatch,":[171],"may":[173],"prove":[174],"generally":[178],"valuable":[179],"diagnostic":[180],"research":[184],".":[185]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}