{"id":"https://openalex.org/W2095085098","doi":"https://doi.org/10.1109/waspaa.2013.6701804","title":"Keynote addresses: From auditory masking to binary classification: Machine learning for speech separation","display_name":"Keynote addresses: From auditory masking to binary classification: Machine learning for speech separation","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2095085098","doi":"https://doi.org/10.1109/waspaa.2013.6701804","mag":"2095085098"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2013.6701804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","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/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064880163","display_name":"Rainer Martin","orcid":"https://orcid.org/0000-0002-9587-4215"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Martin","raw_affiliation_strings":["Ruhr-Universität Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ruhr-Universität Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015405966","display_name":"Peter Vary","orcid":"https://orcid.org/0000-0002-5213-1825"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Vary","raw_affiliation_strings":["RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois, USA","Univ. of Illinois, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]},{"raw_affiliation_string":"Univ. of Illinois, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9891999959945679,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9890000224113464,"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":0.7660294771194458},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6980129480361938},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.6283475160598755},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6163681745529175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6105931401252747},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6039899587631226},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5802937746047974},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5670602321624756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123676061630249},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5114037394523621},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.504520058631897},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.48700910806655884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36154770851135254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36086246371269226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1380573809146881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660294771194458},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6980129480361938},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.6283475160598755},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6163681745529175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6105931401252747},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6039899587631226},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5802937746047974},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5670602321624756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123676061630249},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5114037394523621},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.504520058631897},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.48700910806655884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36154770851135254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36086246371269226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1380573809146881},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2013.6701804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1522062127","https://openalex.org/W2088740872","https://openalex.org/W2153297815","https://openalex.org/W2074134755","https://openalex.org/W3004910802","https://openalex.org/W2293043088","https://openalex.org/W614920976","https://openalex.org/W2467504442","https://openalex.org/W3015973934","https://openalex.org/W1570838609"],"abstract_inverted_index":{"Speech":[0],"separation,":[1],"or":[2],"the":[3,14,18,22,28,39,53,60,68,101,105,127,139],"cocktail":[4],"party":[5],"problem,":[6],"is":[7,37,48,113],"a":[8,35,74,85,110,186],"widely":[9],"acknowledged":[10],"challenge.":[11],"Part":[12],"of":[13,20,30,188],"challenge":[15],"stems":[16],"from":[17],"confusion":[19],"what":[21,52],"computational":[23,78],"goal":[24,76],"should":[25],"be.":[26],"While":[27],"separation":[29,90,196],"every":[31],"sound":[32],"source":[33],"in":[34,197],"mixture":[36],"considered":[38],"gold":[40],"standard,":[41],"I":[42,120],"argue":[43],"that":[44,91],"such":[45],"an":[46],"objective":[47],"neither":[49],"realistic":[50],"nor":[51],"human":[54],"auditory":[55,61,79],"system":[56],"does.":[57],"Motivated":[58],"by":[59,100],"masking":[62],"phenomenon,":[63],"we":[64],"have":[65],"suggested":[66],"instead":[67],"ideal":[69,140],"time-frequency":[70,93],"binary":[71,141],"mask":[72],"as":[73],"main":[75],"for":[77,183],"scene":[80],"analysis.":[81],"This":[82],"leads":[83],"to":[84,88,115,124,137,148,150,159,161],"new":[86,198],"formulation":[87],"speech":[89,103],"classifies":[92],"units":[94],"into":[95],"two":[96],"classes:":[97],"those":[98],"dominated":[99],"target":[102],"and":[104,154,176,180],"rest.":[106],"In":[107],"supervised":[108],"learning,":[109],"paramount":[111],"issue":[112,129],"generalization":[114,128],"conditions":[116],"unseen":[117,151,162],"during":[118],"training.":[119],"describe":[121],"novel":[122],"methods":[123],"deal":[125],"with":[126],"where":[130],"support":[131],"vector":[132],"machines":[133],"(SVMs)":[134],"are":[135],"used":[136],"estimate":[138],"mask.":[142],"One":[143],"method":[144,165],"employs":[145],"distribution":[146],"fitting":[147],"adapt":[149,160],"signal-to-noise":[152],"ratios":[153],"iterative":[155],"voice":[156],"activity":[157],"detection":[158],"noises.":[163],"Another":[164],"learns":[166],"more":[167],"linearly":[168],"separable":[169],"features":[170],"using":[171],"deep":[172],"neural":[173],"networks":[174],"(DNNs)":[175],"then":[177],"couples":[178],"DNN":[179],"linear":[181],"SVM":[182],"training":[184],"on":[185],"variety":[187],"noisy":[189],"conditions.":[190],"Systematic":[191],"evaluations":[192],"show":[193],"high":[194],"quality":[195],"acoustic":[199],"environments.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}