{"id":"https://openalex.org/W2403787182","doi":"https://doi.org/10.21437/interspeech.2014-151","title":"Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling","display_name":"Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2403787182","doi":"https://doi.org/10.21437/interspeech.2014-151","mag":"2403787182"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-151","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5030512300","display_name":"J\u00fcrgen T. Geiger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00fcrgen T. Geiger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"631","last_page":"635"},"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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":0.7415687441825867},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.7295447587966919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7059006690979004},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6197194457054138},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5695943236351013},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5559136867523193},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46008989214897156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31786221265792847},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29239755868911743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415687441825867},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.7295447587966919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7059006690979004},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6197194457054138},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5695943236351013},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5559136867523193},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46008989214897156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31786221265792847},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29239755868911743},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-151","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.180","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ//pdf/14/14gei5.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1993882792","https://openalex.org/W2005638789","https://openalex.org/W2009934439","https://openalex.org/W2047954119","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2070707809","https://openalex.org/W2075888317","https://openalex.org/W2101045344","https://openalex.org/W2104448323","https://openalex.org/W2115730999","https://openalex.org/W2117172387","https://openalex.org/W2131774270","https://openalex.org/W2133676762","https://openalex.org/W2136922672","https://openalex.org/W2143612262","https://openalex.org/W2152051032","https://openalex.org/W2160815625","https://openalex.org/W2328757576","https://openalex.org/W2336741987","https://openalex.org/W2394967684"],"related_works":["https://openalex.org/W2566606998","https://openalex.org/W2406264770","https://openalex.org/W2963920996","https://openalex.org/W1489125746","https://openalex.org/W4366149782","https://openalex.org/W2782005958","https://openalex.org/W1897240248","https://openalex.org/W4297665160","https://openalex.org/W3103945224","https://openalex.org/W2755891984"],"abstract_inverted_index":{"One":[0,69],"method":[1],"to":[2,15,32,99,115,126,183],"achieve":[3],"robust":[4,193],"speech":[5,66,144,194],"recognition":[6,67,136],"in":[7,38,44,82,119,124,146,165],"adverse":[8],"conditions":[9],"including":[10],"noise":[11],"and":[12,149],"reverberation":[13],"is":[14,74,93],"employ":[16],"acoustic":[17,80,191],"modelling":[18,88],"techniques":[19],"involving":[20],"neural":[21,29,196],"networks.":[22],"Using":[23],"long":[24,198],"short-term":[25,199],"memory":[26,200],"(LSTM)":[27],"recurrent":[28],"networks":[30,50,118,175,179],"proved":[31],"be":[33],"efficient":[34],"for":[35,41,63,158,186],"this":[36,72,111,187],"task":[37],"a":[39,45,52,64,78,120,147],"setup":[40,103,170],"phoneme":[42,159],"prediction":[43,162,174],"multi-stream":[46,84],"GMM-HMM":[47],"framework.":[48,85],"These":[49],"exploit":[51],"self-learnt":[53],"amount":[54],"of":[55,71,77,90,138,154],"temporal":[56],"context,":[57],"which":[58],"makes":[59],"them":[60],"especially":[61],"suited":[62],"noisy":[65,150],"task.":[68],"shortcoming":[70],"approach":[73],"the":[75,83,91,100,105,134,139,166],"necessity":[76],"GMM":[79],"model":[81],"Furthermore,":[86],"potential":[87],"power":[89],"network":[92,106,156],"lost":[94],"when":[95],"predicting":[96,180],"phonemes,":[97,181],"compared":[98],"classical":[101],"hybrid":[102,121,167],"where":[104],"predicts":[107],"HMM":[108,122],"states.":[109],"In":[110],"work,":[112],"we":[113],"propose":[114],"use":[116],"LSTM":[117],"setup,":[123],"order":[125],"overcome":[127],"these":[128],"drawbacks.":[129],"Experiments":[130],"are":[131],"performed":[132],"using":[133],"medium-vocabulary":[135],"track":[137],"2nd":[140],"CHiME":[141],"challenge,":[142],"containing":[143],"utterances":[145],"reverberant":[148],"environment.":[151],"A":[152],"comparison":[153],"different":[155],"topologies":[157],"or":[160,168],"state":[161,173],"used":[163],"either":[164],"double-stream":[169],"shows":[171],"that":[172],"perform":[176],"better":[177],"than":[178],"leading":[182],"stateof-the-art":[184],"results":[185],"database.":[188],"Index":[189],"Terms:":[190],"modelling,":[192],"recognition,":[195],"networks,":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}