{"id":"https://openalex.org/W2404724332","doi":"https://doi.org/10.1109/icassp.2016.7472136","title":"Discriminative deep recurrent neural networks for monaural speech separation","display_name":"Discriminative deep recurrent neural networks for monaural speech separation","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2404724332","doi":"https://doi.org/10.1109/icassp.2016.7472136","mag":"2404724332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043206189","display_name":"Guanxiang Wang","orcid":"https://orcid.org/0000-0002-3495-6647"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Guan-Xiang Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, ROC","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088916925","display_name":"Chung-Chien Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Chien Hsu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, ROC","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, ROC","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2544","last_page":"2548"},"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":0.9988999962806702,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9987999796867371,"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/monaural","display_name":"Monaural","score":0.9318252801895142},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7503241300582886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7174609899520874},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6084129810333252},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.584685742855072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669288635253906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5383322238922119},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5111084580421448},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4422876238822937},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.43690991401672363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.304647833108902}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9318252801895142},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7503241300582886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174609899520874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6084129810333252},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.584685742855072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669288635253906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5383322238922119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5111084580421448},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4422876238822937},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.43690991401672363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.304647833108902}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W2029862345","https://openalex.org/W2031647436","https://openalex.org/W2045956438","https://openalex.org/W2046869671","https://openalex.org/W2053165762","https://openalex.org/W2078528584","https://openalex.org/W2099904336","https://openalex.org/W2102017903","https://openalex.org/W2105288628","https://openalex.org/W2107789863","https://openalex.org/W2113907273","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2143169494","https://openalex.org/W2149757909","https://openalex.org/W2150415460","https://openalex.org/W2156387975","https://openalex.org/W2160813409","https://openalex.org/W2183821610","https://openalex.org/W2405589348","https://openalex.org/W6607486085","https://openalex.org/W6675112735","https://openalex.org/W6676071220","https://openalex.org/W6682889407","https://openalex.org/W6713519970"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Deep":[0],"neural":[1,24],"network":[2,25],"is":[3,34,85],"now":[4],"a":[5,20,39,53,122],"new":[6],"trend":[7],"towards":[8],"solving":[9],"different":[10],"problems":[11],"in":[12,132],"speech":[13,30,148],"processing.":[14],"In":[15,136],"this":[16],"paper,":[17],"we":[18,68,139],"propose":[19],"discriminative":[21],"deep":[22,45],"recurrent":[23],"(DRNN)":[26],"model":[27,41],"for":[28,49,147],"monaural":[29,133],"separation.":[31,135],"Our":[32],"idea":[33],"to":[35,42,91,128],"construct":[36],"DRNN":[37,70],"as":[38,121,127],"regression":[40],"discover":[43],"the":[44,61,86,92,97,100,105,113,137,141,144,152],"structure":[46],"and":[47],"regularity":[48],"signal":[50],"reconstruction":[51,88],"from":[52],"mixture":[54],"of":[55,81,124,143],"two":[56,65,82,109],"source":[57,94,110,134],"spectra.":[58],"To":[59],"reinforce":[60],"discrimination":[62,101,118],"capability":[63],"between":[64,108],"separated":[66],"spectra,":[67],"estimate":[69],"separation":[71,131,149],"parameters":[72],"by":[73],"minimizing":[74],"an":[75],"integrated":[76],"objective":[77],"function":[78],"which":[79,103],"consists":[80],"measurements.":[83],"One":[84],"within-source":[87],"errors":[89],"due":[90],"individual":[93],"spectra":[95,111],"while":[96],"other":[98,153],"conveys":[99],"information":[102,119],"preserves":[104],"mutual":[106],"difference":[107],"during":[112],"supervised":[114],"training":[115],"procedure.":[116],"This":[117],"acts":[120],"kind":[123],"regularization":[125],"so":[126],"maintain":[129],"between-source":[130],"experiments,":[138],"demonstrate":[140],"effectiveness":[142],"proposed":[145],"method":[146],"compared":[150],"with":[151],"methods.":[154]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}