{"id":"https://openalex.org/W2697044473","doi":"https://doi.org/10.1109/icassp.2017.7953164","title":"End-to-end speech recognition and keyword search on low-resource languages","display_name":"End-to-end speech recognition and keyword search on low-resource languages","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2697044473","doi":"https://doi.org/10.1109/icassp.2017.7953164","mag":"2697044473"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"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":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"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":["IBM TJ Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5280","last_page":"5284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.8642159700393677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6400359869003296},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5828738808631897},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.504245400428772},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48458850383758545},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4829677641391754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.473150372505188},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4559992849826813},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4553722143173218},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4371633231639862},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4256206154823303},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.42449888586997986},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.300790935754776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.224834144115448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8642159700393677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6400359869003296},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5828738808631897},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.504245400428772},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48458850383758545},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4829677641391754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.473150372505188},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4559992849826813},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4553722143173218},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4371633231639862},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4256206154823303},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.42449888586997986},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.300790935754776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.224834144115448},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1855892484","https://openalex.org/W1872348600","https://openalex.org/W1970064959","https://openalex.org/W2056346282","https://openalex.org/W2080401855","https://openalex.org/W2109886035","https://openalex.org/W2127141656","https://openalex.org/W2155117693","https://openalex.org/W2157331557","https://openalex.org/W2187428966","https://openalex.org/W2193413348","https://openalex.org/W2291975472","https://openalex.org/W2296590378","https://openalex.org/W2397766809","https://openalex.org/W2403195671","https://openalex.org/W2407420912","https://openalex.org/W2510459131","https://openalex.org/W2519224033","https://openalex.org/W2953022181","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963217176","https://openalex.org/W2963403664","https://openalex.org/W2963490782","https://openalex.org/W6623517193","https://openalex.org/W6676562027","https://openalex.org/W6713813099","https://openalex.org/W6726720044"],"related_works":["https://openalex.org/W2766204198","https://openalex.org/W2074671152","https://openalex.org/W1506255978","https://openalex.org/W2117462502","https://openalex.org/W2111928547","https://openalex.org/W2146324774","https://openalex.org/W2938873567","https://openalex.org/W2916997151","https://openalex.org/W2748309409","https://openalex.org/W2949174760"],"abstract_inverted_index":{"In":[0,66],"recent":[1],"years,":[2],"so-called,":[3],"\u201cend-to-end\u201d":[4,157],"speech":[5,25,33,91,160],"recognition":[6,34,92,161],"systems":[7,48,86,100],"have":[8],"emerged":[9],"as":[10],"viable":[11],"alternatives":[12],"to":[13,36,129],"traditional":[14],"ASR":[15,50,85],"frameworks.":[16],"Keyword":[17],"search,":[18],"localizing":[19],"an":[20,38],"orthographic":[21],"query":[22],"in":[23,59],"a":[24,125],"corpus,":[26],"is":[27,119],"typically":[28],"performed":[29],"by":[30],"using":[31,156],"automatic":[32],"(ASR)":[35],"generate":[37,102,113],"index.":[39],"Previous":[40],"work":[41],"has":[42],"evaluated":[43],"the":[44,71,142,153],"use":[45,72],"of":[46,73,127],"end-to-end":[47,84,99],"for":[49,87,121,159],"on":[51,93,107,141,165],"well":[52],"known":[53],"corpora":[54],"(WSJ,":[55],"Switchboard,":[56],"TIMIT,":[57],"etc.)":[58],"high-resource":[60],"languages":[61,146],"like":[62],"English":[63],"and":[64,90,147,162],"Mandarin.":[65],"this":[67,131],"work,":[68],"we":[69],"investigate":[70],"Connectionist":[74],"Temporal":[75],"Classification":[76],"(CTC)":[77],"networks,":[78],"recurrent":[79],"encoder-decoders":[80],"with":[81,133],"attention,":[82],"two":[83],"keyword":[88,163],"search":[89,164],"low":[94],"resource":[95],"languages.":[96,167],"We":[97,123],"find":[98],"can":[101],"high":[103],"quality":[104],"1-best":[105],"transcripts":[106],"low-resource":[108,166],"languages,":[109],"but,":[110],"because":[111],"they":[112],"very":[114],"sharp":[115],"posteriors,":[116],"their":[117],"utility":[118],"limited":[120],"KWS.":[122],"explore":[124],"number":[126],"ways":[128],"address":[130],"limitation":[132],"modest":[134],"success.":[135],"Experimental":[136],"results":[137,155],"reported":[138],"are":[139],"based":[140],"IARPA":[143],"BABEL":[144],"OP3":[145],"evaluation":[148],"framework.":[149],"This":[150],"paper":[151],"represents":[152],"first":[154],"techniques":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}