{"id":"https://openalex.org/W2405158679","doi":"https://doi.org/10.21437/interspeech.2015-634","title":"The IBM BOLT speech transcription system","display_name":"The IBM BOLT speech transcription system","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2405158679","doi":"https://doi.org/10.21437/interspeech.2015-634","mag":"2405158679"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-634","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Kwang J. Kuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019973376","display_name":"Lidia Mangu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lidia Mangu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2255,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91054994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3150","last_page":"3153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8553137183189392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7357330918312073},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7266001105308533},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6789640188217163},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6712626814842224},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.627723217010498},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6043211221694946},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5567491054534912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5542049407958984},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5528881549835205},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5230528116226196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5197470188140869},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5068803429603577},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5056705474853516},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37851205468177795},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08400982618331909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553137183189392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7357330918312073},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7266001105308533},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6789640188217163},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6712626814842224},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.627723217010498},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6043211221694946},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5567491054534912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5542049407958984},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5528881549835205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5230528116226196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5197470188140869},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5068803429603577},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5056705474853516},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37851205468177795},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08400982618331909},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","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":2,"locations":[{"id":"doi:10.21437/interspeech.2015-634","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.7421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.7421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/ibm_bolt.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W396690109","https://openalex.org/W1536583098","https://openalex.org/W1970689298","https://openalex.org/W1993561131","https://openalex.org/W2028706510","https://openalex.org/W2050971845","https://openalex.org/W2077853988","https://openalex.org/W2109613320","https://openalex.org/W2112796928","https://openalex.org/W2117238933","https://openalex.org/W2140679639","https://openalex.org/W2144790469","https://openalex.org/W2152263452","https://openalex.org/W2155117693","https://openalex.org/W2158195707","https://openalex.org/W2294692935","https://openalex.org/W2403195671"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2114483840","https://openalex.org/W2010917994","https://openalex.org/W2129812225","https://openalex.org/W2100475772","https://openalex.org/W4290708361","https://openalex.org/W26527944"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,10,36,92,102,108],"IBM":[3],"automatic":[4],"speech":[5,26,140],"recognition":[6,93],"(ASR)":[7],"sys-tem":[8],"for":[9,32,91,107,134],"DARPA":[11],"Broad":[12],"Operational":[13],"Language":[14],"Translation":[15],"(BOLT)":[16],"program.":[17],"The":[18,40,115],"system":[19,42,94,117],"is":[20,43],"used":[21],"to":[22,29],"transcribe":[23],"conversa-tional":[24],"telephone":[25,143],"(CTS)":[27],"prior":[28],"machine":[30,110,148],"translation":[31,111,149],"Phase":[33],"3":[34],"of":[35,46,68,71,78,123],"program\u2019s":[37],"Activity":[38],"A.":[39],"ASR":[41],"a":[44,76,119,127],"com-bination":[45],"novel":[47],"sequence":[48],"trained":[49],"ensemble":[50],"deep":[51,145],"neural":[52,62,80,146],"net-work":[53],"acoustic":[54],"models":[55,64,90],"on":[56,65,97,126],"speaker":[57],"adapted":[58],"features":[59],"and":[60,82,88,104],"convolu-tional":[61],"network":[63,81],"two":[66],"kinds":[67],"spectro-temporal":[69],"representations":[70],"speech,":[72,144],"in":[73],"conjunction":[74],"with":[75],"variety":[77],"class,":[79],"n-gram":[83],"based":[84],"language":[85,89],"models.":[86],"Acoustic":[87],"are":[95],"built":[96],"transcribed":[98],"audio":[99],"released":[100],"under":[101],"program":[103],"further":[105],"opti-mized":[106],"final":[109],"task":[112],"as":[113],"well.":[114],"evalua-tion":[116],"has":[118],"word":[120],"error":[121],"rate":[122],"32.7":[124],"%":[125],"2":[128],"hour":[129],"Egyptian":[130],"Arabic":[131],"development":[132],"set":[133],"this":[135],"task.":[136],"Index":[137],"Terms:":[138],"Automatic":[139],"recognition,":[141],"conversational":[142],"networks,":[147]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
