{"id":"https://openalex.org/W2397226255","doi":"https://doi.org/10.21437/interspeech.2015-358","title":"Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement","display_name":"Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2397226255","doi":"https://doi.org/10.21437/interspeech.2015-358","mag":"2397226255"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-358","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-358","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":"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/A5112124014","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-3601-0246"},"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":true,"raw_author_name":"Yong Xu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, 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"},"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":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101472289","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0002-1772-7674"},"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":"Zhen Huang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"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":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, 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"},"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":["School of Electrical and Computer Engineering, Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112124014"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":9.2662,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.98472975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1508","last_page":"1512"},"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":0.9976999759674072,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822374105453491},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.737088143825531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6457340717315674},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6342871785163879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5596722364425659},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5578909516334534},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5449395179748535},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5284594893455505},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5209875702857971},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49822235107421875},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.486422061920166},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4393869638442993},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41251951456069946},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36943018436431885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31465405225753784},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1504482626914978},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10478243231773376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822374105453491},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.737088143825531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6457340717315674},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6342871785163879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5596722364425659},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5578909516334534},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5449395179748535},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5284594893455505},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5209875702857971},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49822235107421875},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.486422061920166},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4393869638442993},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41251951456069946},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36943018436431885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31465405225753784},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1504482626914978},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10478243231773376},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-358","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-358","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W5151113","https://openalex.org/W104438260","https://openalex.org/W258661521","https://openalex.org/W1552314771","https://openalex.org/W1963950237","https://openalex.org/W1974387177","https://openalex.org/W1989364685","https://openalex.org/W2013608223","https://openalex.org/W2031614119","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2062227835","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2094035326","https://openalex.org/W2095705004","https://openalex.org/W2103075368","https://openalex.org/W2109000787","https://openalex.org/W2121973264","https://openalex.org/W2125324924","https://openalex.org/W2128653836","https://openalex.org/W2141411743","https://openalex.org/W2141493634","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2168379380","https://openalex.org/W2402901296","https://openalex.org/W2403766732","https://openalex.org/W2405774341","https://openalex.org/W2407793339","https://openalex.org/W3147539069","https://openalex.org/W3209042722","https://openalex.org/W4300906944"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W111365173","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,117],"multi-objective":[3],"framework":[4],"to":[5,13,32,53],"learn":[6,54],"both":[7],"secondary":[8,55,114],"targets":[9],"not":[10,95],"directly":[11,35],"related":[12],"the":[14,22,26,38,69,78,87,98,106,109,112,126,143,154],"intended":[15],"task":[16],"of":[17,25,85,101,108,133,153],"speech":[18,40],"enhancement":[19],"(SE)":[20],"and":[21,64,74,103,139,146],"primary":[23,110],"target":[24],"clean":[27],"log-power":[28],"spectra":[29],"(LPS)":[30],"features":[31],"be":[33,120],"used":[34,121],"for":[36,82,122],"constructing":[37],"enhanced":[39],"signals.In":[41],"deep":[42],"neural":[43],"network":[44],"(DNN)":[45],"based":[46],"SE":[47,144],"we":[48],"introduce":[49],"an":[50],"auxiliary":[51],"structure":[52],"continuous":[56],"features,":[57],"such":[58,67],"as":[59,68,116],"mel-frequency":[60],"cepstral":[61],"coefficients":[62],"(MFCCs),":[63],"categorical":[65],"information,":[66],"ideal":[70],"binary":[71],"mask":[72],"(IBM),":[73],"integrate":[75],"it":[76],"into":[77],"original":[79],"DNN":[80],"architecture":[81],"joint":[83,89,137],"optimization":[84],"all":[86],"parameters.This":[88],"estimation":[90],"scheme":[91],"imposes":[92],"additional":[93],"constraints":[94],"available":[96],"in":[97,129],"direct":[99],"prediction":[100],"LPS,":[102],"potentially":[104],"improves":[105,142],"learning":[107,141],"target.Furthermore,":[111],"learned":[113],"information":[115],"byproduct":[118],"can":[119],"other":[123],"purposes,":[124],"e.g.,":[125],"IBM-based":[127,147],"post-processing":[128,148],"this":[130],"work.A":[131],"series":[132],"experiments":[134],"show":[135],"that":[136],"LPS":[138],"MFCC":[140],"performance,":[145],"further":[149],"enhances":[150],"listening":[151],"quality":[152],"reconstructed":[155],"speech.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}