{"id":"https://openalex.org/W2605589342","doi":"https://doi.org/10.1109/hscma.2017.7895577","title":"Multiple-target deep learning for LSTM-RNN based speech enhancement","display_name":"Multiple-target deep learning for LSTM-RNN based speech enhancement","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2605589342","doi":"https://doi.org/10.1109/hscma.2017.7895577","mag":"2605589342"},"language":"en","primary_location":{"id":"doi:10.1109/hscma.2017.7895577","doi":"https://doi.org/10.1109/hscma.2017.7895577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2017.7895577","pdf_url":null,"source":{"id":"https://openalex.org/S7407106439","display_name":"Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Hands-free Speech Communications and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2605589342"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455","observed_orcids":["https://orcid.org/0000-0001-7680-6455"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389","observed_orcids":["https://orcid.org/0000-0002-2387-0389","https://orcid.org/0009-0001-8096-9895"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827","observed_orcids":["https://orcid.org/0000-0002-0859-2827"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551","observed_orcids":["https://orcid.org/0000-0002-1892-2551"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.6331,"has_fulltext":false,"cited_by_count":220,"citation_normalized_percentile":{"value":0.99547794,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-enhancement","display_name":"speech enhancement","score":0.996999979019165},{"id":"https://openalex.org/keywords/lstm-rnn","display_name":"LSTM-RNN","score":0.890999972820282},{"id":"https://openalex.org/keywords/ideal-ratio-mask","display_name":"ideal ratio mask","score":0.9520000219345093},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.8560000061988831},{"id":"https://openalex.org/keywords/low-signal-to-noise-ratio","display_name":"low signal-to-noise ratio","score":0.6000000238418579},{"id":"https://openalex.org/keywords/speech-quality","display_name":"speech quality","score":0.7599999904632568}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8651856184005737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306639194488525},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7049111127853394},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6574166417121887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6454206705093384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953877568244934},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46370938420295715},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37185561656951904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32589173316955566},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15820178389549255},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hscma.2017.7895577","doi":"https://doi.org/10.1109/hscma.2017.7895577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2017.7895577","pdf_url":null,"source":{"id":"https://openalex.org/S7407106439","display_name":"Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Hands-free Speech Communications and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W190004713","https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1689711448","https://openalex.org/W1815076433","https://openalex.org/W1897240248","https://openalex.org/W1974387177","https://openalex.org/W2013608223","https://openalex.org/W2046869671","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2094035326","https://openalex.org/W2094461119","https://openalex.org/W2119796132","https://openalex.org/W2121973264","https://openalex.org/W2136922672","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2168379380","https://openalex.org/W2181607856","https://openalex.org/W2293634267","https://openalex.org/W2397226255","https://openalex.org/W2515930231","https://openalex.org/W3147539069","https://openalex.org/W4239943352","https://openalex.org/W4253928870"],"related_works":["https://openalex.org/W3093346936","https://openalex.org/W7095526055","https://openalex.org/W2900151226","https://openalex.org/W2998155746","https://openalex.org/W2920582663","https://openalex.org/W3111611403","https://openalex.org/W4294706633","https://openalex.org/W3028077980","https://openalex.org/W2952979007","https://openalex.org/W3010411659"],"abstract_inverted_index":{"In":[0],"this":[1,102],"study,":[2],"we":[3],"explore":[4],"long":[5],"short-term":[6],"memory":[7],"recurrent":[8],"neural":[9,41],"networks":[10],"(LSTM-RNNs)":[11],"for":[12,20,130],"speech":[13,29,81,132],"enhancement.":[14],"First,":[15],"a":[16,21,53,104],"regression":[17,45],"LSTM-RNN":[18,62],"approach":[19,91,109],"direct":[22,59,76],"mapping":[23,60,77],"from":[24],"the":[25,57,75,89,119,127],"noisy":[26],"to":[27,35,99],"clean":[28],"features":[30],"is":[31,70,110],"presented":[32],"and":[33,63,124,134],"verified":[34],"be":[36],"more":[37],"effective":[38],"than":[39],"deep":[40],"network":[42],"(DNN)":[43],"based":[44,61,68],"techniques":[46],"in":[47],"modeling":[48],"long-term":[49],"acoustic":[50],"context.":[51],"Then,":[52],"comprehensive":[54],"comparison":[55],"between":[56],"proposed":[58,120],"ideal":[64],"ratio":[65],"mask":[66],"(IRM)":[67],"LSTM-RNNs":[69],"conducted.":[71],"We":[72],"observe":[73],"that":[74,118],"framework":[78,121],"achieves":[79],"better":[80],"intelligibility":[82],"at":[83,95],"low":[84],"signal-to-noise":[85],"ratios":[86],"(SNRs)":[87],"while":[88],"IRM":[90],"shows":[92],"its":[93],"superiority":[94],"high":[96],"SNRs.":[97],"Accordingly,":[98],"fully":[100],"utilize":[101],"complementarity,":[103],"novel":[105],"multiple-target":[106],"joint":[107],"learning":[108],"designed.":[111],"The":[112],"experiments":[113],"under":[114],"unseen":[115],"noises":[116],"show":[117],"can":[122],"consistently":[123],"significantly":[125],"improve":[126],"objective":[128],"measures":[129],"both":[131],"quality":[133],"intelligibility.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":39},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2017-04-28T00:00:00"}
