{"id":"https://openalex.org/W2891237889","doi":"https://doi.org/10.1109/icassp.2018.8462468","title":"Enhancement and Analysis of Conversational Speech: JSALT 2017","display_name":"Enhancement and Analysis of Conversational Speech: JSALT 2017","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891237889","doi":"https://doi.org/10.1109/icassp.2018.8462468","mag":"2891237889"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5084839882","display_name":"Neville Ryanta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neville Ryanta","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I4210120198","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039894584","display_name":"Elika Bergelson","orcid":"https://orcid.org/0000-0003-2742-4797"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elika Bergelson","raw_affiliation_strings":["Department of Psychology and Neuroscience, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Psychology and Neuroscience, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016543371","display_name":"Kenneth Church","orcid":"https://orcid.org/0000-0001-8378-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Church","raw_affiliation_strings":["IBM, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042831132","display_name":"Alejandrina Cristi\u00e0","orcid":"https://orcid.org/0000-0003-2979-4556"},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210151031","display_name":"Laboratoire de Sciences Cognitives et Psycholinguistique","ror":"https://ror.org/05fvhm231","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210096427","https://openalex.org/I4210151031","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alejandrina Cristia","raw_affiliation_strings":["Laboratoire de Sciences Cognitives et Psycholinguistique, ENS, Paris, France"],"affiliations":[{"raw_affiliation_string":"Laboratoire de Sciences Cognitives et Psycholinguistique, ENS, Paris, France","institution_ids":["https://openalex.org/I4210151031","https://openalex.org/I29607241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Electrical Engineering Department, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064747490","display_name":"Diana Kowalski","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diana Kowalski","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085465402","display_name":"Mahesh Krishnamoorthy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahesh Krishnamoorthy","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088087927","display_name":"Rajat Kulshreshta","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajat Kulshreshta","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I4210120198","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062616905","display_name":"Yu-Ding Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ding Lu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054649622","display_name":"Matthew Maciejewski","orcid":"https://orcid.org/0000-0002-6336-2135"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Maciejewski","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054937420","display_name":"J\u00e1n Profant","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Profant","raw_affiliation_strings":["Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I4210120198","https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Department of Computer Science, University of California Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":6,"institutions_distinct_count":18,"corresponding_author_ids":["https://openalex.org/A5084839882"],"corresponding_institution_ids":["https://openalex.org/I4210120198","https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":1.4863,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83690247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5154","last_page":"5158"},"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/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/computer-science","display_name":"Computer science","score":0.6314325332641602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4737711250782013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6314325332641602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4737711250782013}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1499712254","https://openalex.org/W1558276682","https://openalex.org/W1561065572","https://openalex.org/W1600744878","https://openalex.org/W1635512741","https://openalex.org/W1965819578","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2064675550","https://openalex.org/W2078528584","https://openalex.org/W2083384274","https://openalex.org/W2083751884","https://openalex.org/W2086139506","https://openalex.org/W2090056283","https://openalex.org/W2115483887","https://openalex.org/W2121973264","https://openalex.org/W2153894152","https://openalex.org/W2169264834","https://openalex.org/W2510280606","https://openalex.org/W2516547830","https://openalex.org/W2605589342","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2796868621","https://openalex.org/W2797412426","https://openalex.org/W2963446712","https://openalex.org/W3147539069","https://openalex.org/W4255455116","https://openalex.org/W4293257135","https://openalex.org/W6629903641","https://openalex.org/W6633191483","https://openalex.org/W6641449205","https://openalex.org/W6673243767","https://openalex.org/W6677264727","https://openalex.org/W6684539355","https://openalex.org/W6684823487","https://openalex.org/W6725739302","https://openalex.org/W6740167877","https://openalex.org/W6750150874","https://openalex.org/W6750633417"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,15,63,129],"recognition":[2],"is":[3,23,29,39],"more":[4,6],"and":[5,8,45,60,81,125,137],"widely":[7],"effectively":[9],"used.":[10],"Nevertheless,":[11],"in":[12,96],"some":[13],"automatic":[14],"analysis":[16],"tasks":[17],"the":[18,21,31,86,90,113,116,134],"state":[19,114],"of":[20,27,33,101,107,112,115,119,122,127],"art":[22],"surprisingly":[24],"poor.":[25],"One":[26],"these":[28],"\u201cdiarization\u201d,":[30],"task":[32],"determining":[34],"who":[35],"spoke":[36],"when.":[37],"Diarization":[38],"key":[40],"to":[41,144],"processing":[42],"meeting":[43],"audio":[44],"clinical":[46],"interviews,":[47],"extended":[48],"recordings":[49],"such":[50],"as":[51],"police":[52],"body":[53],"cam":[54],"or":[55],"child":[56],"language":[57],"acquisition":[58],"data,":[59],"any":[61],"other":[62],"data":[64],"involving":[65],"multiple":[66],"speakers":[67],"whose":[68],"voices":[69],"are":[70],"not":[71],"cleanly":[72],"separated":[73],"into":[74],"individual":[75],"channels.":[76],"Overlapping":[77],"speech,":[78],"environmental":[79],"noise":[80],"suboptimal":[82],"recording":[83],"techniques":[84],"make":[85],"problem":[87],"harder.":[88],"During":[89],"JSALT":[91],"Summer":[92],"Workshop":[93],"at":[94],"CMU":[95],"2017,":[97],"an":[98],"international":[99],"team":[100],"researchers":[102],"worked":[103],"on":[104],"several":[105],"aspects":[106],"this":[108],"problem,":[109],"including":[110],"calibration":[111],"art,":[117],"detection":[118],"overlaps,":[120],"enhancement":[121],"noisy":[123],"recordings,":[124],"classification":[126],"shorter":[128],"segments.":[130],"This":[131],"paper":[132],"sketches":[133],"workshop's":[135],"results,":[136],"announces":[138],"plans":[139],"for":[140],"a":[141],"\u201cDiarization":[142],"Challenge\u201d":[143],"encourage":[145],"further":[146],"progress.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
