{"id":"https://openalex.org/W2801144864","doi":"https://doi.org/10.1109/icassp.2018.8461563","title":"Hybrid Lstm-Fsmn Networks for Acoustic Modeling","display_name":"Hybrid Lstm-Fsmn Networks for Acoustic Modeling","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801144864","doi":"https://doi.org/10.1109/icassp.2018.8461563","mag":"2801144864"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5047650531","display_name":"Asa Oines","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095816","display_name":"Tianjin Tianhe Hospital","ror":"https://ror.org/00k5k8k03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095816"]},{"id":"https://openalex.org/I5740404","display_name":"Tianjin Medical University","ror":"https://ror.org/02mh8wx89","country_code":"CN","type":"education","lineage":["https://openalex.org/I5740404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Asa Oines","raw_affiliation_strings":["Tianiin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianiin University, Tianjin, China","institution_ids":["https://openalex.org/I4210095816","https://openalex.org/I5740404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095816","display_name":"Tianjin Tianhe Hospital","ror":"https://ror.org/00k5k8k03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095816"]},{"id":"https://openalex.org/I5740404","display_name":"Tianjin Medical University","ror":"https://ror.org/02mh8wx89","country_code":"CN","type":"education","lineage":["https://openalex.org/I5740404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Eugene Weinstein","raw_affiliation_strings":["Tianiin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianiin University, Tianjin, China","institution_ids":["https://openalex.org/I4210095816","https://openalex.org/I5740404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095816","display_name":"Tianjin Tianhe Hospital","ror":"https://ror.org/00k5k8k03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095816"]},{"id":"https://openalex.org/I5740404","display_name":"Tianjin Medical University","ror":"https://ror.org/02mh8wx89","country_code":"CN","type":"education","lineage":["https://openalex.org/I5740404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pedro Moreno","raw_affiliation_strings":["Tianiin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianiin University, Tianjin, China","institution_ids":["https://openalex.org/I4210095816","https://openalex.org/I5740404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5844","last_page":"5848"},"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":0.9998999834060669,"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":0.9987999796867371,"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":0.8263740539550781},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6907469034194946},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6238003969192505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5848749279975891},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5578382611274719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5368462204933167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5203004479408264},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.5123182535171509},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45959222316741943},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42664211988449097},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.4170980453491211},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3481904864311218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07752540707588196},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.06549909710884094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263740539550781},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6907469034194946},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6238003969192505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5848749279975891},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5578382611274719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5368462204933167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5203004479408264},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.5123182535171509},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45959222316741943},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42664211988449097},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.4170980453491211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3481904864311218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07752540707588196},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.06549909710884094},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":18,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1689711448","https://openalex.org/W2013598660","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2136439176","https://openalex.org/W2150355110","https://openalex.org/W2168231600","https://openalex.org/W2208299922","https://openalex.org/W2291513470","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2478884216","https://openalex.org/W2517251061","https://openalex.org/W2590320937","https://openalex.org/W6637409405","https://openalex.org/W6653897473","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W2912831041","https://openalex.org/W3173606726"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,39,62,101],"series":[4],"of":[5,54,66,94,103,114],"experiments":[6,75],"with":[7,25,91],"neural":[8],"networks":[9],"containing":[10],"long":[11],"short-term":[12],"memory":[13,19],"(LSTM)":[14],"[1]":[15],"and":[16],"feedforward":[17],"sequential":[18],"network":[20,59],"(FSMN)":[21],"[2]-[4]":[22],"layers":[23,56],"trained":[24],"the":[26,58,88,104,112,115],"connectionist":[27],"temporal":[28],"classification":[29],"(CTC)":[30],"[5]":[31],"criteria":[32],"for":[33,70],"acoustic":[34,50,79],"modeling.":[35],"We":[36,85],"propose":[37],"using":[38],"hybrid":[40],"LSTM/FSMN":[41],"(FLMN)":[42],"architecture":[43,90,106],"as":[44],"an":[45],"enhancement":[46],"to":[47,60],"conventional":[48,83],"LSTM-only":[49],"models.":[51],"The":[52],"addition":[53],"FSMN":[55,105,116],"allows":[57],"model":[61],"fixed":[63],"size":[64],"representation":[65],"future":[67,96],"context":[68],"suitable":[69],"online":[71],"speech":[72],"recognition.":[73],"Our":[74],"show":[76],"that":[77,107],"FLMN":[78,89],"models":[80],"significantly":[81],"outperform":[82],"LSTM.":[84],"also":[86],"compare":[87],"other":[92],"methods":[93],"modeling":[95],"context.":[97],"Finally,":[98],"we":[99],"present":[100],"modification":[102],"improves":[108],"performance":[109],"by":[110],"reducing":[111],"width":[113],"output.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
