{"id":"https://openalex.org/W2786031273","doi":"https://doi.org/10.1109/asru.2017.8268932","title":"Syllable-based acoustic modeling with CTC-SMBR-LSTM","display_name":"Syllable-based acoustic modeling with CTC-SMBR-LSTM","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786031273","doi":"https://doi.org/10.1109/asru.2017.8268932","mag":"2786031273"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268932","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/A5008909213","display_name":"Zhongdi Qu","orcid":"https://orcid.org/0009-0002-7789-712X"},"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":"Zhongdi Qu","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","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":"Parisa Haghani","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","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":"Eugene Weinstein","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","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":"Pedro Moreno","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"177"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9987000226974487,"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":0.790096640586853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7226787805557251},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.667543351650238},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.646331787109375},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6088911294937134},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6024311780929565},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4916308522224426},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.47406286001205444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45664283633232117},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4279186725616455},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34657609462738037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08317998051643372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790096640586853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7226787805557251},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.667543351650238},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.646331787109375},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6088911294937134},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6024311780929565},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4916308522224426},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.47406286001205444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45664283633232117},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4279186725616455},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34657609462738037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08317998051643372},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268932","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W1489125746","https://openalex.org/W1974979586","https://openalex.org/W2064675550","https://openalex.org/W2096466030","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2158069733","https://openalex.org/W2167200294","https://openalex.org/W2169455968","https://openalex.org/W2193413348","https://openalex.org/W2291513470","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2294962864","https://openalex.org/W2395416438","https://openalex.org/W2401055968","https://openalex.org/W2888226713","https://openalex.org/W2963920996","https://openalex.org/W6600588093","https://openalex.org/W6629052376","https://openalex.org/W6687566353","https://openalex.org/W6696934422","https://openalex.org/W6696982659","https://openalex.org/W6753776127","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W2154156780","https://openalex.org/W3096664139","https://openalex.org/W4385890381"],"abstract_inverted_index":{"We":[0,188],"explore":[1],"the":[2,31,41,45,53,57,133,196],"feasibility":[3],"of":[4,26,33,44,56,135],"training":[5],"long":[6],"short-term":[7],"memory":[8],"(LSTM)":[9],"recurrent":[10],"neural":[11],"networks":[12],"(RNNs)":[13],"with":[14,72,174,181,185],"syllables,":[15],"rather":[16,116],"than":[17,117,156,180],"phonemes,":[18,118],"as":[19,36,47,166],"outputs.":[20,140],"Syllables":[21],"are":[22,70,193],"a":[23,91,122,144],"natural":[24],"choice":[25],"linguistic":[27],"unit":[28],"for":[29,60,66,95,113],"modeling":[30,114],"acoustics":[32],"languages":[34,62],"such":[35,61],"Mandarin":[37,145,203],"Chinese,":[38],"due":[39],"to":[40,128,200],"inherent":[42],"nature":[43],"syllable":[46,58],"an":[48],"elemental":[49],"pronunciation":[50],"construct":[51],"and":[52,77,161,205],"limited":[54],"size":[55],"set":[59],"(around":[63],"1400":[64],"syllables":[65,115,131,204],"Mandarin).":[67],"Our":[68,98,141],"models":[69,100,152,176,183],"trained":[71,199],"Connectionist":[73],"Temporal":[74],"Classification":[75],"(CTC)":[76],"state-level":[78],"minimum":[79],"Bayes":[80],"risk":[81],"(sMBR)":[82],"loss":[83],"using":[84],"asynchronous":[85],"stochastic":[86],"gradient":[87],"descent":[88],"(ASGD)":[89],"utilizing":[90],"parallel":[92],"computation":[93],"infrastructure":[94],"large-scale":[96],"training.":[97],"acoustic":[99],"operate":[101],"on":[102,143],"feature":[103],"frames":[104],"computed":[105],"every":[106],"30ms,":[107],"which":[108,119],"makes":[109],"them":[110],"well":[111],"suited":[112],"can":[120,153,162],"have":[121,132],"shorter":[123],"duration.":[124],"Additionally,":[125,172],"when":[126,195],"compared":[127],"wordlevel":[129],"modeling,":[130],"advantage":[134],"avoiding":[136],"out-of-vocabulary":[137],"(OOV)":[138],"model":[139,197],"experiments":[142],"voice":[146],"search":[147],"task":[148],"show":[149],"that":[150,190],"syllable-output":[151,175],"perform":[154],"better":[155],"context-independent":[157],"(CI)":[158],"phone-output":[159],"models,":[160],"give":[163],"similar":[164],"performance":[165],"our":[167],"state-of-the-art":[168],"context-dependent":[169],"(CD)":[170],"models.":[171,187],"decoding":[173],"is":[177,198],"substantially":[178],"faster":[179],"CI":[182],"or":[184],"CD":[186],"demonstrate":[189],"these":[191],"improvements":[192],"maintained":[194],"recognize":[201],"both":[202],"English":[206],"phonemes.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}