{"id":"https://openalex.org/W4396519789","doi":"https://doi.org/10.1007/s12559-024-10288-y","title":"Towards Efficient Recurrent Architectures: A Deep LSTM Neural Network Applied to Speech Enhancement and Recognition","display_name":"Towards Efficient Recurrent Architectures: A Deep LSTM Neural Network Applied to Speech Enhancement and Recognition","publication_year":2024,"publication_date":"2024-04-30","ids":{"openalex":"https://openalex.org/W4396519789","doi":"https://doi.org/10.1007/s12559-024-10288-y"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-024-10288-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-024-10288-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10288-y.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10288-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100378706","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-3958-7198"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Materials Science and Engineering, Yunnan University, Kunming City, Yunnan Province, China"],"affiliations":[{"raw_affiliation_string":"School of Materials Science and Engineering, Yunnan University, Kunming City, Yunnan Province, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059780753","display_name":"Nasir Saleem","orcid":"https://orcid.org/0000-0003-0010-0629"},"institutions":[{"id":"https://openalex.org/I172324550","display_name":"Gomal University","ror":"https://ror.org/0241b8f19","country_code":"PK","type":"education","lineage":["https://openalex.org/I172324550"]},{"id":"https://openalex.org/I4164984","display_name":"International Islamic University Malaysia","ror":"https://ror.org/03s9hs139","country_code":"MY","type":"education","lineage":["https://openalex.org/I4164984"]}],"countries":["MY","PK"],"is_corresponding":true,"raw_author_name":"Nasir Saleem","raw_affiliation_strings":["Department of Electrical Engineering, Faculty of Engineering and Technology, Gomal University, Dera Ismail Khan, 29050, Pakistan","Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Faculty of Engineering and Technology, Gomal University, Dera Ismail Khan, 29050, Pakistan","institution_ids":["https://openalex.org/I172324550"]},{"raw_affiliation_string":"Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I4164984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031234998","display_name":"Teddy Surya Gunawan","orcid":"https://orcid.org/0000-0003-3345-4669"},"institutions":[{"id":"https://openalex.org/I4164984","display_name":"International Islamic University Malaysia","ror":"https://ror.org/03s9hs139","country_code":"MY","type":"education","lineage":["https://openalex.org/I4164984"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Teddy Surya Gunawan","raw_affiliation_strings":["Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I4164984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059780753"],"corresponding_institution_ids":["https://openalex.org/I172324550","https://openalex.org/I4164984"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":6.2128,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97244157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"3","first_page":"1221","last_page":"1236"},"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":0.9994000196456909,"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":0.9993000030517578,"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/pesq","display_name":"PESQ","score":0.9728919267654419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8348566293716431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6611539125442505},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6399709582328796},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5661918520927429},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.548150360584259},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4587453007698059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4556974470615387},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43423426151275635},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.28085070848464966},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21259436011314392}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9728919267654419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348566293716431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6611539125442505},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6399709582328796},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5661918520927429},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.548150360584259},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4587453007698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4556974470615387},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43423426151275635},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28085070848464966},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21259436011314392},{"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":2,"locations":[{"id":"doi:10.1007/s12559-024-10288-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-024-10288-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10288-y.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},{"id":"pmh:oai:generic.eprints.org:112153","is_oa":true,"landing_page_url":null,"pdf_url":"http://irep.iium.edu.my/112153/2/112153_Towards%20efficient%20recurrent%20architectures_SCOPUS.pdf","source":{"id":"https://openalex.org/S4306400713","display_name":"The International Islamic University Malaysia Repository (The International Islamic University Malaysia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4164984","host_organization_name":"International Islamic University Malaysia","host_organization_lineage":["https://openalex.org/I4164984"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1007/s12559-024-10288-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-024-10288-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-024-10288-y.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396519789.pdf","grobid_xml":"https://content.openalex.org/works/W4396519789.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1606614440","https://openalex.org/W1635512741","https://openalex.org/W1952824372","https://openalex.org/W1974387177","https://openalex.org/W1985258458","https://openalex.org/W1995536493","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2122364000","https://openalex.org/W2128653836","https://openalex.org/W2527993301","https://openalex.org/W2550397165","https://openalex.org/W2593463961","https://openalex.org/W2678916739","https://openalex.org/W2725516257","https://openalex.org/W2775798474","https://openalex.org/W2802304149","https://openalex.org/W2894982555","https://openalex.org/W2940177920","https://openalex.org/W2954198060","https://openalex.org/W2962883855","https://openalex.org/W2963341071","https://openalex.org/W3011475824","https://openalex.org/W3028019732","https://openalex.org/W3036598372","https://openalex.org/W3045520545","https://openalex.org/W3082512732","https://openalex.org/W3086513098","https://openalex.org/W3088145342","https://openalex.org/W3093346936","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3097283596","https://openalex.org/W3097945073","https://openalex.org/W3111611403","https://openalex.org/W3129077738","https://openalex.org/W3147539069","https://openalex.org/W3197034572","https://openalex.org/W3211438798","https://openalex.org/W4200079780","https://openalex.org/W4213129550","https://openalex.org/W4221149546","https://openalex.org/W4225583202","https://openalex.org/W4285389493","https://openalex.org/W4302383814","https://openalex.org/W4309259952","https://openalex.org/W4311088617","https://openalex.org/W4376456759","https://openalex.org/W4387872955","https://openalex.org/W6600336842","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W2037635165","https://openalex.org/W4200562864","https://openalex.org/W2153897396","https://openalex.org/W2157102033"],"abstract_inverted_index":{"Long":[0],"short-term":[1],"memory":[2],"(LSTM)":[3],"has":[4],"proven":[5],"effective":[6],"in":[7,16,27,37,56,78,178,184,217],"modeling":[8,32],"sequential":[9],"data.":[10,62],"However,":[11],"it":[12,93],"may":[13],"encounter":[14],"challenges":[15],"accurately":[17],"capturing":[18,34,48],"long-term":[19,49],"temporal":[20,35,50],"dependencies.":[21],"LSTM":[22,45,88,148,210,249],"plays":[23],"a":[24,43,175,181,257],"central":[25],"role":[26],"speech":[28,38,136,152,168,229],"enhancement":[29],"by":[30,52],"effectively":[31],"and":[33,84,113,124,139,154,167,180,197,203,220],"dependencies":[36,51],"signals.":[39],"This":[40],"paper":[41],"introduces":[42],"variable-neurons-based":[44],"designed":[46],"for":[47,95,110,241],"reducing":[53],"neuron":[54],"representation":[55],"layers":[57,68],"with":[58,191],"no":[59],"loss":[60],"of":[61,135,201],"A":[63],"skip":[64],"connection":[65],"between":[66],"nonadjacent":[67],"is":[69,89,239],"added":[70],"to":[71],"prevent":[72],"gradient":[73],"vanishing.":[74],"An":[75],"attention":[76],"mechanism":[77],"these":[79],"connections":[80],"highlights":[81],"important":[82],"features":[83],"spectral":[85],"components.":[86],"Our":[87],"inherently":[90],"causal,":[91],"making":[92],"well-suited":[94],"real-time":[96],"processing":[97],"without":[98],"relying":[99],"on":[100,186,233],"future":[101],"information.":[102],"Training":[103],"involves":[104],"utilizing":[105],"combined":[106],"acoustic":[107],"feature":[108],"sets":[109],"improved":[111],"performance,":[112,161],"the":[114,125,146,187,192,195,236,251],"models":[115],"estimate":[116],"two":[117],"time\u2013frequency":[118],"masks\u2014the":[119],"ideal":[120,126],"ratio":[121],"mask":[122,128],"(IRM)":[123],"binary":[127],"(IBM).":[129],"Comprehensive":[130],"evaluation":[131,134],"using":[132],"perceptual":[133,155],"quality":[137],"(PESQ)":[138],"short-time":[140],"objective":[141],"intelligibility":[142,153],"(STOI)":[143],"showed":[144,174,199],"that":[145],"proposed":[147,172,209,248],"architecture":[149,211],"demonstrates":[150],"enhanced":[151,234],"quality.":[156],"Composite":[157],"measures":[158],"further":[159],"substantiated":[160],"considering":[162],"residual":[163],"noise":[164],"distortion":[165,169],"(Cbak)":[166],"(Csig).":[170],"The":[171,208,247],"model":[173],"16.21%":[176],"improvement":[177,183],"STOI":[179,196],"0.69":[182],"PESQ":[185,198],"TIMIT":[188],"database.":[189],"Similarly,":[190],"LibriSpeech":[193],"database,":[194],"improvements":[200],"16.41%":[202],"0.71":[204],"over":[205],"noisy":[206,223,263],"mixtures.":[207],"outperforms":[212],"deep":[213],"neural":[214],"networks":[215],"(DNNs)":[216],"different":[218,262],"stationary":[219],"nonstationary":[221],"background":[222],"conditions.":[224],"To":[225],"train":[226],"an":[227],"automatic":[228],"recognition":[230],"(ASR)":[231],"system":[232],"speech,":[235],"Kaldi":[237],"toolkit":[238],"used":[240],"evaluating":[242],"word":[243],"error":[244],"rate":[245],"(WER).":[246],"at":[250],"front-end":[252],"notably":[253],"reduced":[254],"WERs,":[255],"achieving":[256],"notable":[258],"15.13%":[259],"WER":[260],"across":[261],"backgrounds.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}