{"id":"https://openalex.org/W2545177271","doi":"https://doi.org/10.21437/interspeech.2017-1566","title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","display_name":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2545177271","doi":"https://doi.org/10.21437/interspeech.2017-1566","mag":"2545177271"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1566","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1566","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/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hank Liao","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ha\u015fim Sak","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010878109"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":38.8097,"has_fulltext":false,"cited_by_count":298,"citation_normalized_percentile":{"value":0.99789767,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3707","last_page":"3711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976999759674072,"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":0.9929999709129333,"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/speech-recognition","display_name":"Speech recognition","score":0.8120160102844238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7957552671432495},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6024602055549622},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5544895529747009},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5303270220756531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4183615446090698},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41629207134246826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3899731934070587},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3482086658477783},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.30569207668304443},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14179623126983643}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8120160102844238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957552671432495},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6024602055549622},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5544895529747009},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5303270220756531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4183615446090698},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41629207134246826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3899731934070587},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3482086658477783},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30569207668304443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14179623126983643},{"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.2017-1566","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1566","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1494198834","https://openalex.org/W1525636403","https://openalex.org/W1533416326","https://openalex.org/W1736701665","https://openalex.org/W1966147466","https://openalex.org/W2033256038","https://openalex.org/W2048060899","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2109886035","https://openalex.org/W2131774270","https://openalex.org/W2158069733","https://openalex.org/W2168231600","https://openalex.org/W2193413348","https://openalex.org/W2293634267","https://openalex.org/W2294962864","https://openalex.org/W2327501763","https://openalex.org/W2507287275","https://openalex.org/W2608712415","https://openalex.org/W2963403664"],"related_works":["https://openalex.org/W1987021544","https://openalex.org/W2759980945","https://openalex.org/W2331981651","https://openalex.org/W2620660273","https://openalex.org/W2240622083","https://openalex.org/W3089379469","https://openalex.org/W2001537489","https://openalex.org/W2376203252","https://openalex.org/W82600882","https://openalex.org/W2286739582"],"abstract_inverted_index":{"We":[0],"present":[1],"results":[2],"that":[3,67,91,107],"show":[4,66],"it":[5],"is":[6,44],"possible":[7],"to":[8,57,104],"build":[9],"a":[10,93,115],"competitive,":[11],"greatly":[12],"simplified,":[13],"large":[14],"vocabulary":[15,29],"continuous":[16],"speech":[17,79],"recognition":[18,80],"system":[19],"with":[20,40,121],"whole":[21],"words":[22,33],"as":[23,75],"acoustic":[24,51],"units.We":[25],"model":[26,43,81,100],"the":[27,59,68,83,102,108],"output":[28],"of":[30,49,85],"about":[31],"100,000":[32],"directly":[34],"using":[35],"deep":[36],"bi-directional":[37],"LSTM":[38],"RNNs":[39],"CTC":[41,69,109],"loss.The":[42],"trained":[45],"on":[46],"125,000":[47],"hours":[48],"semi-supervised":[50],"training":[52],"data,":[53],"which":[54],"enables":[55],"us":[56],"alleviate":[58],"data":[60],"sparsity":[61],"problem":[62],"for":[63],"word":[64,70,110],"models.We":[65],"models":[71,111],"work":[72],"very":[73],"well":[74],"an":[76],"end-to-end":[77],"all-neural":[78],"without":[82,97],"use":[84],"traditional":[86],"context-dependent":[87],"sub-word":[88,122],"phone":[89],"units":[90],"require":[92],"pronunciation":[94],"lexicon,":[95],"and":[96],"any":[98],"language":[99],"removing":[101],"need":[103],"decode.We":[105],"demonstrate":[106],"perform":[112],"better":[113],"than":[114],"strong,":[116],"more":[117],"complex,":[118],"state-of-the-art":[119],"baseline":[120],"units.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":44},{"year":2019,"cited_by_count":77},{"year":2018,"cited_by_count":54},{"year":2017,"cited_by_count":24}],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2025-10-10T00:00:00"}