{"id":"https://openalex.org/W2597757402","doi":"https://doi.org/10.21437/interspeech.2017-546","title":"Direct Acoustics-to-Word Models for English Conversational Speech Recognition","display_name":"Direct Acoustics-to-Word Models for English Conversational Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2597757402","doi":"https://doi.org/10.21437/interspeech.2017-546","mag":"2597757402"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007586881","display_name":"D. Nahamoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Nahamoo","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015927589"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":17.3567,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.99326455,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"959","last_page":"963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9909999966621399,"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/speech-recognition","display_name":"Speech recognition","score":0.7496000528335571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060384750366211},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5600402355194092},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39559149742126465},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3309776186943054},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22254863381385803}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7496000528335571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060384750366211},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5600402355194092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39559149742126465},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3309776186943054},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22254863381385803},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/interspeech.2017-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1489125746","https://openalex.org/W1508165687","https://openalex.org/W1526990717","https://openalex.org/W1614298861","https://openalex.org/W1736701665","https://openalex.org/W1922655562","https://openalex.org/W2050971845","https://openalex.org/W2102113734","https://openalex.org/W2109886035","https://openalex.org/W2133564696","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2185726469","https://openalex.org/W2250539671","https://openalex.org/W2293858598","https://openalex.org/W2395416438","https://openalex.org/W2408289839","https://openalex.org/W2521999726","https://openalex.org/W2545177271","https://openalex.org/W2603679025","https://openalex.org/W2611669587","https://openalex.org/W2916979304","https://openalex.org/W2963266252","https://openalex.org/W4302296459"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W2970166416"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,74,167],"end-to-end":[3,47],"automatic":[4],"speech":[5,98],"recognition":[6],"(ASR)":[7],"has":[8],"shown":[9],"that":[10],"the":[11,49,66,104,144,174,182],"connectionist":[12],"temporal":[13],"classification":[14],"(CTC)":[15],"loss":[16],"can":[17],"be":[18],"used":[19,30],"to":[20,23,39,55,103,120,124,130,172],"convert":[21],"acoustics":[22,53],"phone":[24,60,187],"or":[25,89,152],"character":[26],"sequences.Such":[27],"systems":[28],"are":[29,44],"with":[31,99,155,159],"a":[32,91,138,160,178],"dictionary":[33],"and":[34,81,95,180,186],"separately-trained":[35],"Language":[36],"Model":[37],"(LM)":[38],"produce":[40],"word":[41,108,112,135,139,169,185],"sequences.However,":[42],"they":[43],"not":[45,85],"truly":[46],"in":[48],"sense":[50],"of":[51,107,116,142,177,184],"mapping":[52],"directly":[54],"words":[56],"without":[57,149],"an":[58,87],"intermediate":[59],"representation.In":[61],"this":[62,132],"paper,":[63],"we":[64],"present":[65,127,164],"first":[67],"results":[68,166],"employing":[69],"direct":[70],"acoustics-to-word":[71],"CTC":[72,111,134,158,168,188],"models":[73,83,113],"two":[75],"well-known":[76],"public":[77],"benchmark":[78],"tasks:":[79],"Switchboard":[80],"Call-Home.These":[82],"do":[84],"require":[86,114],"LM":[88,151],"even":[90],"decoder":[92,153],"at":[93],"run-time":[94],"hence":[96],"recognize":[97],"minimal":[100],"complexity.However,":[101],"due":[102],"large":[105],"number":[106],"output":[109],"units,":[110],"orders":[115],"magnitude":[117],"more":[118],"data":[119],"train":[121],"reliably":[122],"compared":[123,154],"traditional":[125],"systems.We":[126],"some":[128],"techniques":[129],"mitigate":[131],"issue.Our":[133],"model":[136,170],"achieves":[137],"error":[140],"rate":[141],"13.0%/18.8%on":[143],"Hub5-2000":[145],"Switchboard/CallHome":[146],"test":[147],"sets":[148],"any":[150],"9.6%/16.0%for":[156],"phone-based":[157],"4-gram":[161],"LM.We":[162],"also":[163],"rescoring":[165],"lattices":[171],"quantify":[173],"performance":[175,183],"benefits":[176],"LM,":[179],"contrast":[181],"models.":[189]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}