{"id":"https://openalex.org/W2768808476","doi":"https://doi.org/10.1109/sips.2017.8110005","title":"Monaural speaker separation using source-contrastive estimation","display_name":"Monaural speaker separation using source-contrastive estimation","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2768808476","doi":"https://doi.org/10.1109/sips.2017.8110005","mag":"2768808476"},"language":"en","primary_location":{"id":"doi:10.1109/sips.2017.8110005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips.2017.8110005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Workshop on Signal Processing Systems (SiPS)","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/A5080560015","display_name":"Cory Stephenson","orcid":"https://orcid.org/0000-0003-0078-6501"},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cory Stephenson","raw_affiliation_strings":["Lab41, In-Q-Tel Laboratories, CA"],"affiliations":[{"raw_affiliation_string":"Lab41, In-Q-Tel Laboratories, CA","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038340888","display_name":"Patrick Callier","orcid":"https://orcid.org/0000-0002-9794-1848"},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Callier","raw_affiliation_strings":["Lab41, In-Q-Tel Laboratories, CA"],"affiliations":[{"raw_affiliation_string":"Lab41, In-Q-Tel Laboratories, CA","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077756706","display_name":"Abhinav Ganesh","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Ganesh","raw_affiliation_strings":["Lab41, In-Q-Tel Laboratories, CA"],"affiliations":[{"raw_affiliation_string":"Lab41, In-Q-Tel Laboratories, CA","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110791031","display_name":"Karl Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Ni","raw_affiliation_strings":["Lab41, In-Q-Tel Laboratories, CA"],"affiliations":[{"raw_affiliation_string":"Lab41, In-Q-Tel Laboratories, CA","institution_ids":["https://openalex.org/I38260057"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080560015"],"corresponding_institution_ids":["https://openalex.org/I38260057"],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4767129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9950000047683716,"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":0.8553103804588318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7199727296829224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6171365976333618},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44649237394332886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3744872808456421}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8553103804588318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199727296829224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6171365976333618},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44649237394332886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3744872808456421}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips.2017.8110005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips.2017.8110005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Workshop on Signal Processing Systems (SiPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1994923416","https://openalex.org/W2069681747","https://openalex.org/W2098950531","https://openalex.org/W2132304835","https://openalex.org/W2144763279","https://openalex.org/W2150415460","https://openalex.org/W2153579005","https://openalex.org/W2221409856","https://openalex.org/W2404974779","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2563106974","https://openalex.org/W2962715207","https://openalex.org/W4294170691","https://openalex.org/W6679813350","https://openalex.org/W6682691769","https://openalex.org/W6718827390","https://openalex.org/W6730148858","https://openalex.org/W6731435466"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2401567014","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2955471771"],"abstract_inverted_index":{"We":[0,57,159],"propose":[1],"an":[2,79,198],"algorithm":[3,196],"to":[4,29,132,149,203],"separate":[5],"simultaneously":[6],"speaking":[7],"persons":[8],"from":[9],"each":[10],"other,":[11],"the":[12,95,99,113,162,189,204],"\u201ccocktail":[13],"party":[14,206],"problem\u201d,":[15],"using":[16],"a":[17,23,30,40,87,105,175],"single":[18],"microphone.":[19],"Our":[20,128,195],"approach":[21,129],"involves":[22],"deep":[24,134],"recurrent":[25],"neural":[26,135],"networks":[27],"regression":[28],"vector":[31,41,90,176],"space":[32,42,177],"that":[33,122],"is":[34,50,65,81,102,125,130],"descriptive":[35],"of":[36,107,166,181],"independent":[37],"speakers.":[38,158],"Such":[39],"can":[43],"embed":[44],"empirically":[45],"determined":[46,97],"speaker":[47,55,152],"characteristics":[48],"and":[49,85,138,147,208],"optimized":[51],"by":[52,67,83,98,173],"distinguishing":[53],"between":[54],"masks.":[56],"call":[58],"this":[59],"technique":[60],"source-contrastive":[61],"estimation.":[62],"The":[63],"methodology":[64],"inspired":[66],"negative":[68],"sampling,":[69],"which":[70],"has":[71],"seen":[72],"success":[73],"in":[74],"natural":[75],"language":[76],"processing,":[77],"where":[78],"embedding":[80],"learned":[82],"correlating":[84],"decorrelating":[86],"given":[88],"input":[89,114],"with":[91,169],"output":[92,100],"weights.":[93],"Although":[94],"matrix":[96],"weights":[101],"dependent":[103],"on":[104],"set":[106],"known":[108],"speakers,":[109],"we":[110,142,187],"only":[111],"use":[112,143],"vectors":[115],"during":[116,193],"inference.":[117],"Doing":[118],"so":[119],"will":[120],"ensure":[121],"source":[123],"separation":[124],"explicitly":[126],"speaker-independent.":[127],"similar":[131],"recent":[133],"network":[136],"clustering":[137],"permutation-invariant":[139],"training":[140,174],"research;":[141],"weighted":[144],"spectral":[145],"features":[146],"masks":[148],"augment":[150],"individual":[151],"frequencies":[153],"while":[154],"filtering":[155],"out":[156],"other":[157,167,216],"avoid,":[160],"however,":[161],"severe":[163],"computational":[164],"burden":[165],"approaches":[168],"our":[170],"technique.":[171],"Furthermore,":[172],"rather":[178],"than":[179,215],"combinations":[180],"different":[182],"speakers":[183],"or":[184],"differences":[185],"thereof,":[186],"avoid":[188],"so-called":[190],"permutation":[191],"problem":[192],"training.":[194],"offers":[197],"intuitive,":[199],"computationally":[200],"efficient":[201],"response":[202],"cocktail":[205],"problem,":[207],"most":[209],"importantly":[210],"boasts":[211],"better":[212],"empirical":[213],"performance":[214],"current":[217],"techniques.":[218]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}