{"id":"https://openalex.org/W4256071232","doi":"https://doi.org/10.1109/waspaa.2013.6701900","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/W4256071232","doi":"https://doi.org/10.1109/waspaa.2013.6701900"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2013.6701900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701900","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-abstract","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":true,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051837453"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"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":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9621999859809875,"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":0.9589999914169312,"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/computer-science","display_name":"Computer science","score":0.7599220275878906},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7171237468719482},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6332764625549316},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6218147277832031},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.6078368425369263},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5993857383728027},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5961900353431702},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.556729793548584},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5075281858444214},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5030907988548279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.499434232711792},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49784064292907715},{"id":"https://openalex.org/keywords/binary-decision-diagram","display_name":"Binary decision diagram","score":0.41996920108795166},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.41650110483169556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3787422478199005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33962613344192505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2020370066165924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14235037565231323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599220275878906},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7171237468719482},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6332764625549316},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6218147277832031},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.6078368425369263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5993857383728027},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5961900353431702},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.556729793548584},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5075281858444214},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5030907988548279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499434232711792},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49784064292907715},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.41996920108795166},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.41650110483169556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3787422478199005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33962613344192505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2020370066165924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14235037565231323},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2013.6701900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701900","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":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/W1570838609","https://openalex.org/W2168793898"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"Speech":[4],"separation,":[5],"or":[6],"the":[7,18,22,26,32,43,57,64,72,105,109,131,143],"cocktail":[8],"party":[9],"problem,":[10],"is":[11,41,52,117],"a":[12,39,78,89,114,190],"widely":[13],"acknowledged":[14],"challenge.":[15],"Part":[16],"of":[17,24,34,192],"challenge":[19],"stems":[20],"from":[21],"confusion":[23],"what":[25,56],"computational":[27,82],"goal":[28,80],"should":[29],"be.":[30],"While":[31],"separation":[33,94,200],"every":[35],"sound":[36],"source":[37],"in":[38,201],"mixture":[40],"considered":[42],"gold":[44],"standard,":[45],"I":[46,124],"argue":[47],"that":[48,95],"such":[49],"an":[50],"objective":[51],"neither":[53],"realistic":[54],"nor":[55],"human":[58],"auditory":[59,65,83],"system":[60],"does.":[61],"Motivated":[62],"by":[63,104],"masking":[66],"phenomenon,":[67],"we":[68],"have":[69],"suggested":[70],"instead":[71],"ideal":[73,144],"time-frequency":[74,97],"binary":[75,145],"mask":[76],"as":[77],"main":[79],"for":[81,187],"scene":[84],"analysis.":[85],"This":[86],"leads":[87],"to":[88,92,119,128,141,152,154,163,165],"new":[90,202],"formulation":[91],"speech":[93,107],"classifies":[96],"units":[98],"into":[99],"two":[100],"classes:":[101],"those":[102],"dominated":[103],"target":[106],"and":[108,158,180,184],"rest.":[110],"In":[111],"supervised":[112],"learning,":[113],"paramount":[115],"issue":[116,133],"generalization":[118,132],"conditions":[120],"unseen":[121,155,166],"during":[122],"training.":[123],"describe":[125],"novel":[126],"methods":[127],"deal":[129],"with":[130],"where":[134],"support":[135],"vector":[136],"machines":[137],"(SVMs)":[138],"are":[139],"used":[140],"estimate":[142],"mask.":[146],"One":[147],"method":[148,169],"employs":[149],"distribution":[150],"fitting":[151],"adapt":[153,164],"signal-to-noise":[156],"ratios":[157],"iterative":[159],"voice":[160],"activity":[161],"detection":[162],"noises.":[167],"Another":[168],"learns":[170],"more":[171],"linearly":[172],"separable":[173],"features":[174],"using":[175],"deep":[176],"neural":[177],"networks":[178],"(DNNs)":[179],"then":[181],"couples":[182],"DNN":[183],"linear":[185],"SVM":[186],"training":[188],"on":[189],"variety":[191],"noisy":[193],"conditions.":[194],"Systematic":[195],"evaluations":[196],"show":[197],"high":[198],"quality":[199],"acoustic":[203],"environments.":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}