{"id":"https://openalex.org/W2755891984","doi":"https://doi.org/10.21437/interspeech.2015-659","title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","display_name":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2755891984","doi":"https://doi.org/10.21437/interspeech.2015-659","mag":"2755891984"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-659","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Columbia University; Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University; Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Mitsubishi Electric Research USA; Sabanci University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA; Sabanci University","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":159,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3274","last_page":"3278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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":0.9961000084877014,"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":0.8295846581459045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7910184860229492},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7218820452690125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.648131251335144},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6226491332054138},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.619572639465332},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.559161901473999},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5509212017059326},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5075222253799438},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5047200918197632},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4785607159137726},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.464011549949646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4451794922351837},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4380420446395874},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4298769235610962},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3475215435028076},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12991657853126526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07785412669181824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295846581459045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7910184860229492},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7218820452690125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.648131251335144},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6226491332054138},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.619572639465332},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.559161901473999},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5509212017059326},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5075222253799438},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5047200918197632},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4785607159137726},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.464011549949646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4451794922351837},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4380420446395874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4298769235610962},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3475215435028076},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12991657853126526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07785412669181824},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-659","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:research.sabanciuniv.edu:28866","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402254","display_name":"Sabanci University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134235054","host_organization_name":"Sabanc\u0131 \u00dcniversitesi","host_organization_lineage":["https://openalex.org/I134235054"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"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/W1482149378","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W2009934439","https://openalex.org/W2032252376","https://openalex.org/W2046869671","https://openalex.org/W2062164080","https://openalex.org/W2063224314","https://openalex.org/W2101045344","https://openalex.org/W2131342762","https://openalex.org/W2158339352","https://openalex.org/W2160815625","https://openalex.org/W2293009711","https://openalex.org/W2328757576","https://openalex.org/W2403195671","https://openalex.org/W2403787182","https://openalex.org/W2408713104","https://openalex.org/W2762693443"],"related_works":["https://openalex.org/W2962707588","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W2008737763","https://openalex.org/W4367598165"],"abstract_inverted_index":{"Long":[0],"Short-Term":[1],"Memory":[2],"(LSTM)":[3],"recurrent":[4],"neural":[5],"network":[6,131],"has":[7,14],"proven":[8],"effective":[9],"in":[10,18,49],"modeling":[11],"speech":[12,20,25,35,40,142],"and":[13,23,42,63,70,105,115,125,144,148],"achieved":[15],"outstanding":[16],"performance":[17,32],"both":[19],"enhancement":[21,41],"(SE)":[22],"automatic":[24],"recognition":[26,43,145],"(ASR).":[27],"To":[28],"further":[29],"improve":[30],"the":[31,88,139],"of":[33,39,61,82,112],"noise-robust":[34,94],"recognition,":[36],"a":[37,109,127],"combination":[38],"was":[44],"shown":[45],"to":[46,55,87,153],"be":[47],"promising":[48],"earlier":[50],"work.":[51],"This":[52],"paper":[53],"aims":[54],"explore":[56],"options":[57],"for":[58,93],"consistent":[59],"integration":[60,83,101],"SE":[62,69,114],"ASR":[64,71,95,116],"using":[65],"LSTM":[66,130],"networks.":[67],"Since":[68],"have":[72],"different":[73],"objective":[74],"criteria,":[75],"it":[76],"is":[77],"not":[78],"clear":[79],"what":[80],"kind":[81],"would":[84],"finally":[85],"lead":[86],"best":[89],"word":[90],"error":[91],"rate":[92],"tasks.":[96],"In":[97],"this":[98],"work,":[99],"several":[100],"architectures":[102],"are":[103],"proposed":[104,134],"tested,":[106],"including:":[107],"(1)":[108],"pipeline":[110],"architecture":[111],"LSTM-based":[113],"with":[117],"sequence":[118],"training,":[119],"(2)":[120],"an":[121],"alternating":[122],"estimation":[123],"architecture,":[124],"(3)":[126],"multi-task":[128],"hybrid":[129],"architecture.":[132],"The":[133],"models":[135],"were":[136],"evaluated":[137],"on":[138],"2nd":[140],"CHiME":[141],"separation":[143],"challenge":[146],"task,":[147],"show":[149],"significant":[150],"improvements":[151],"relative":[152],"prior":[154],"results.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}