{"id":"https://openalex.org/W2963827914","doi":"https://doi.org/10.1109/asru.2017.8268937","title":"Exploring neural transducers for end-to-end speech recognition","display_name":"Exploring neural transducers for end-to-end speech recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2963827914","doi":"https://doi.org/10.1109/asru.2017.8268937","mag":"2963827914"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268937","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5056579280","display_name":"Eric Battenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Eric Battenberg","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084512458","display_name":"Rewon Child","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rewon Child","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103153292","display_name":"Adam Coates","orcid":"https://orcid.org/0000-0002-4004-1603"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Adam Coates","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036251807","display_name":"Yashesh Gaur Yi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur Yi Li","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089361846","display_name":"Hairong Liu","orcid":"https://orcid.org/0000-0002-7971-8634"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hairong Liu","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090158590","display_name":"Sanjeev Satheesh","orcid":"https://orcid.org/0009-0008-5139-1036"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanjeev Satheesh","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047764126","display_name":"Anuroop Sriram","orcid":"https://orcid.org/0000-0001-6295-7535"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anuroop Sriram","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041599050","display_name":"Zhenyao Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyao Zhu","raw_affiliation_strings":["Baidu Silicon Valley AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Silicon Valley AI Lab","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":234,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"206","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9983000159263611,"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":0.9976000189781189,"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":0.7864614129066467},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7860227823257446},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7672338485717773},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7298423647880554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6642212867736816},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6447160840034485},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6364299058914185},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6288729310035706},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5924103260040283},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5000553131103516},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.4752497375011444},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44720447063446045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40882959961891174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15340963006019592},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11281523108482361},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07019391655921936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864614129066467},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7860227823257446},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7672338485717773},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7298423647880554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6642212867736816},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6447160840034485},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6364299058914185},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6288729310035706},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5924103260040283},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5000553131103516},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.4752497375011444},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44720447063446045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40882959961891174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15340963006019592},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11281523108482361},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07019391655921936},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268937","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1710082047","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2102113734","https://openalex.org/W2109886035","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2170716095","https://openalex.org/W2184045248","https://openalex.org/W2193413348","https://openalex.org/W2291022022","https://openalex.org/W2291513470","https://openalex.org/W2514741789","https://openalex.org/W2520160253","https://openalex.org/W2521999726","https://openalex.org/W2525778437","https://openalex.org/W2533523411","https://openalex.org/W2551620312","https://openalex.org/W2559302184","https://openalex.org/W2577366047","https://openalex.org/W2594856242","https://openalex.org/W2605141709","https://openalex.org/W2614038158","https://openalex.org/W2647484625","https://openalex.org/W2953022181","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963795358","https://openalex.org/W4299435467","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6676562027"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W2160451571","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"perform":[4],"an":[5],"empirical":[6],"comparison":[7],"among":[8],"the":[9,33,43,74,94,100,103,118],"CTC,":[10],"RNN-Transducer,":[11],"and":[12,28,114],"attention-based":[13],"Seq2Seq":[14,27],"models":[15,30,37,57,105],"for":[16],"end-to-end":[17],"speech":[18,75],"recognition.":[19],"We":[20,90],"show":[21],"that,":[22],"without":[23],"any":[24],"language":[25,40,61],"model,":[26,41],"RNN-Transducer":[29,56],"both":[31],"outperform":[32,66],"best":[34,68],"reported":[35],"CTC":[36,69],"with":[38,59],"a":[39,60],"on":[42],"popular":[44],"Hub5'00":[45],"benchmark.":[46],"On":[47],"our":[48,67],"internal":[49],"diverse":[50],"dataset,":[51],"these":[52],"trends":[53],"continue":[54],"\u2014":[55,106],"rescored":[58],"model":[62],"after":[63],"beam":[64],"search":[65],"models.":[70],"These":[71],"results":[72],"simplify":[73],"recognition":[76],"pipeline":[77],"so":[78],"that":[79],"decoding":[80],"can":[81],"now":[82],"be":[83],"expressed":[84],"purely":[85],"as":[86],"neural":[87],"network":[88],"operations.":[89],"also":[91],"study":[92],"how":[93],"choice":[95],"of":[96,102],"encoder":[97,109],"architecture":[98],"affects":[99],"performance":[101],"three":[104],"when":[107,115],"all":[108],"layers":[110],"are":[111],"forward":[112],"only,":[113],"encoders":[116],"downsample":[117],"input":[119],"representation":[120],"aggressively.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":54},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}