{"id":"https://openalex.org/W2924115626","doi":"https://doi.org/10.1109/icassp.2019.8683874","title":"Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss","display_name":"Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2924115626","doi":"https://doi.org/10.1109/icassp.2019.8683874","mag":"2924115626"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Temasek Laboratories@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5089,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.9737659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.9378998279571533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699229717254639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6202842593193054},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.574409008026123},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5220677256584167},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.4851273000240326},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4694397449493408},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45907896757125854},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43905389308929443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37434881925582886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3591606318950653},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33707374334335327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1187523901462555},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07945427298545837}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9378998279571533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699229717254639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6202842593193054},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.574409008026123},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5220677256584167},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.4851273000240326},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4694397449493408},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45907896757125854},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43905389308929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37434881925582886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3591606318950653},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33707374334335327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1187523901462555},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07945427298545837},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1985371235","https://openalex.org/W1994396704","https://openalex.org/W2069681747","https://openalex.org/W2079623482","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2397725648","https://openalex.org/W2403307129","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2766901645","https://openalex.org/W2800022361","https://openalex.org/W2889029567","https://openalex.org/W2891054259","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2911612049","https://openalex.org/W2962715207","https://openalex.org/W2964121744","https://openalex.org/W2964238697","https://openalex.org/W6631190155","https://openalex.org/W6688843265","https://openalex.org/W6713701104","https://openalex.org/W6758235888"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4386746628","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W2546593254","https://openalex.org/W3209446892","https://openalex.org/W2792294082"],"abstract_inverted_index":{"The":[0,27],"SpeakerBeam-FE":[1],"(SBF)":[2],"method":[3,93,114,151],"is":[4,33],"proposed":[5,113,150],"for":[6,67,152],"speaker":[7,70,73,97],"extraction.":[8],"It":[9],"attempts":[10],"to":[11,61,94],"overcome":[12],"the":[13,44,68,72,84,91,100,112,122,149],"problem":[14],"of":[15,18,31,83,132],"unknown":[16],"number":[17],"speakers":[19],"in":[20,90],"an":[21],"audio":[22],"recording":[23],"during":[24],"source":[25],"separation.":[26],"mask":[28,66,101],"approximation":[29,59],"loss":[30,60],"SBF":[32,92,123],"sub-optimal,":[34],"which":[35],"doesn't":[36],"calculate":[37],"direct":[38],"signal":[39],"reconstruction":[40],"error":[41],"and":[42,56,117,129,142,154],"consider":[43],"speech":[45,133],"context.":[46],"To":[47],"address":[48],"these":[49],"problems,":[50],"this":[51,76],"paper":[52,77],"proposes":[53],"a":[54,63,79,96],"magnitude":[55],"temporal":[57],"spectrum":[58],"estimate":[62],"phase":[64],"sensitive":[65],"target":[69],"with":[71],"characteristics.":[74],"Moreover,":[75],"explores":[78],"concatenation":[80],"framework":[81],"instead":[82],"context":[85],"adaptive":[86],"deep":[87],"neural":[88],"network":[89],"encode":[95],"embedding":[98],"into":[99],"estimation":[102],"network.":[103],"Experimental":[104],"results":[105],"under":[106],"open":[107],"evaluation":[108,131],"condition":[109],"show":[110],"that":[111],"achieves":[115],"70.4%":[116],"17.7%":[118],"relative":[119,144],"improvement":[120],"over":[121],"baseline":[124],"on":[125],"signal-to-distortion":[126],"ratio":[127],"(SDR)":[128],"perceptual":[130],"quality":[134],"(PESQ),":[135],"respectively.":[136],"A":[137],"further":[138],"analysis":[139],"demonstrates":[140],"69.1%":[141],"72.3%":[143],"SDR":[145],"improvements":[146],"obtained":[147],"by":[148],"different":[153],"same":[155],"gender":[156],"mixtures.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}