{"id":"https://openalex.org/W2883281347","doi":"https://doi.org/10.1109/taslp.2018.2858923","title":"Learning Self-Informed Feature Contribution for Deep Learning-Based Acoustic Modeling","display_name":"Learning Self-Informed Feature Contribution for Deep Learning-Based Acoustic Modeling","publication_year":2018,"publication_date":"2018-07-24","ids":{"openalex":"https://openalex.org/W2883281347","doi":"https://doi.org/10.1109/taslp.2018.2858923","mag":"2883281347"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2858923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2858923","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5046397537","display_name":"Younggwan Kim","orcid":"https://orcid.org/0000-0003-2053-8521"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younggwan Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2053-8521","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087820105","display_name":"Myungjong Kim","orcid":"https://orcid.org/0000-0003-0756-0177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Myungjong Kim","raw_affiliation_strings":["Avoma, Inc., Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0756-0177","affiliations":[{"raw_affiliation_string":"Avoma, Inc., Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054193752","display_name":"Jahyun Goo","orcid":"https://orcid.org/0000-0002-7373-289X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jahyun Goo","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066573438","display_name":"Hoirin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoirin Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8787-6982","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.6341,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69505589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"26","issue":"11","first_page":"2204","last_page":"2214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8367259502410889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7042306065559387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6669604182243347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6196486353874207},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6105319261550903},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5605143904685974},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.559569776058197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5212869644165039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5027279853820801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.462078332901001},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44066178798675537},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43413329124450684},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.42782294750213623},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.4161667227745056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38392752408981323},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12048840522766113}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8367259502410889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042306065559387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6669604182243347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6196486353874207},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6105319261550903},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5605143904685974},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.559569776058197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5212869644165039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5027279853820801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.462078332901001},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44066178798675537},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43413329124450684},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.42782294750213623},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.4161667227745056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38392752408981323},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12048840522766113},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2858923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2858923","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W567546468","https://openalex.org/W1524333225","https://openalex.org/W1583145088","https://openalex.org/W1600744878","https://openalex.org/W1736701665","https://openalex.org/W1779452081","https://openalex.org/W1917432393","https://openalex.org/W1932968309","https://openalex.org/W1970088388","https://openalex.org/W1973681148","https://openalex.org/W1976114481","https://openalex.org/W1993882792","https://openalex.org/W1995562189","https://openalex.org/W2002342963","https://openalex.org/W2044893557","https://openalex.org/W2048526313","https://openalex.org/W2057826000","https://openalex.org/W2079623482","https://openalex.org/W2085628288","https://openalex.org/W2105833168","https://openalex.org/W2113890143","https://openalex.org/W2123237149","https://openalex.org/W2131342762","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2168249605","https://openalex.org/W2170541567","https://openalex.org/W2184045248","https://openalex.org/W2250357346","https://openalex.org/W2291598608","https://openalex.org/W2291652038","https://openalex.org/W2293634267","https://openalex.org/W2295119550","https://openalex.org/W2296167893","https://openalex.org/W2327501763","https://openalex.org/W2339611261","https://openalex.org/W2399979637","https://openalex.org/W2404620314","https://openalex.org/W2508048623","https://openalex.org/W2515753980","https://openalex.org/W2530876040","https://openalex.org/W2658929981","https://openalex.org/W2785600113","https://openalex.org/W2917668649","https://openalex.org/W2962816167","https://openalex.org/W2963211739","https://openalex.org/W2998216295","https://openalex.org/W4285719527","https://openalex.org/W4297797495","https://openalex.org/W6603403951","https://openalex.org/W6615969787","https://openalex.org/W6631362777","https://openalex.org/W6638005537","https://openalex.org/W6678292227","https://openalex.org/W6679429981","https://openalex.org/W6691509046","https://openalex.org/W6696934422","https://openalex.org/W6697090674","https://openalex.org/W6712582510","https://openalex.org/W6714125293","https://openalex.org/W6724883057","https://openalex.org/W6759815381","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3199964822","https://openalex.org/W4232132981","https://openalex.org/W4238046985","https://openalex.org/W3164948662","https://openalex.org/W3003242282","https://openalex.org/W3153597579","https://openalex.org/W3012824888","https://openalex.org/W2998249245"],"abstract_inverted_index":{"In":[0,46,82],"this":[1,21],"paper,":[2],"we":[3,23,84],"introduce":[4],"a":[5,32,87],"new":[6],"feature":[7,18,33],"engineering":[8],"approach":[9],"for":[10,90],"deep":[11,27],"learning-based":[12],"acoustic":[13,62],"modeling,":[14],"which":[15,93],"utilizes":[16],"input":[17,58,80],"contributions.":[19],"For":[20],"purpose,":[22],"propose":[24,86],"an":[25,61],"auxiliary":[26],"neural":[28],"network":[29,35,64],"(DNN)":[30],"called":[31],"contribution":[34,44,76],"(FCN)":[36],"whose":[37],"output":[38],"layer":[39],"is":[40,66],"composed":[41],"of":[42,57,102],"sigmoid-based":[43],"gates.":[45,104],"our":[47],"framework,":[48],"the":[49,91,95,99,103,111,118,135],"FCN":[50,96],"tries":[51],"to":[52,97,121],"learn":[53],"element-level":[54],"discriminative":[55],"contributions":[56],"features":[59,70],"and":[60,79,123],"model":[63],"(AMN)":[65],"trained":[67],"by":[68,72],"gated":[69],"generated":[71],"element-wise":[73],"multiplication":[74],"between":[75],"gate":[77],"outputs":[78],"features.":[81],"addition,":[83],"also":[85],"regularization":[88],"method":[89],"FCN,":[92],"helps":[94],"activate":[98],"minimum":[100],"number":[101],"The":[105],"proposed":[106,119],"methods":[107,120],"were":[108],"evaluated":[109],"on":[110],"TED-LIUM":[112],"release":[113],"1":[114],"corpus.":[115],"We":[116],"applied":[117],"DNN-":[122],"long":[124],"short-term":[125],"memory-based":[126],"AMNs.":[127],"Experimental":[128],"results":[129,130],"showed":[131],"that":[132],"AMNs":[133],"with":[134,142],"FCNs":[136],"consistently":[137],"improved":[138],"recognition":[139],"performance":[140],"compared":[141],"AMN-only":[143],"frameworks.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}