{"id":"https://openalex.org/W28743102","doi":"https://doi.org/10.21437/interspeech.2006-19","title":"A computational auditory scene analysis system for robust speech recognition","display_name":"A computational auditory scene analysis system for robust speech recognition","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W28743102","doi":"https://doi.org/10.21437/interspeech.2006-19","mag":"28743102"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5102163048","display_name":"Soundararajan Srinivasan","orcid":null},"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":"Soundararajan Srinivasan","raw_affiliation_strings":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025797022","display_name":"Zhaozhang Jin","orcid":null},"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":"Zhaozhang Jin","raw_affiliation_strings":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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":["Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1547","last_page":"Mon1WeS.1"},"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":0.9994999766349792,"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":0.9990000128746033,"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/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.8540732860565186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780148983001709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7567223906517029},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.6557199954986572},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.547795295715332},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5067744851112366},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4971473515033722},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4731025695800781},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.4713898301124573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47019729018211365},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4400210976600647},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4299507737159729},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4173547327518463},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4127885699272156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4080374240875244},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4018963873386383},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.1709045171737671},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0945729911327362},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08428674936294556}],"concepts":[{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.8540732860565186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780148983001709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7567223906517029},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.6557199954986572},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.547795295715332},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5067744851112366},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4971473515033722},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4731025695800781},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.4713898301124573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47019729018211365},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4400210976600647},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4299507737159729},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4173547327518463},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4127885699272156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4080374240875244},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4018963873386383},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.1709045171737671},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0945729911327362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08428674936294556},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2006-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.4380","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.4380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~martin/SpeechSeparationChallenge/srinivasan_june.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.7174","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.7174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~jinzh/papers/ssc_osu_is06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W10765870","https://openalex.org/W88864901","https://openalex.org/W111179440","https://openalex.org/W160800111","https://openalex.org/W1575829986","https://openalex.org/W2034040413","https://openalex.org/W2074354966","https://openalex.org/W2097191389","https://openalex.org/W2100692852","https://openalex.org/W2102334473","https://openalex.org/W2123157731","https://openalex.org/W2124260943","https://openalex.org/W2143855671","https://openalex.org/W2146608839","https://openalex.org/W2147442641","https://openalex.org/W2149425615","https://openalex.org/W2157906748","https://openalex.org/W2170256193"],"related_works":["https://openalex.org/W2362704157","https://openalex.org/W3199891340","https://openalex.org/W133022121","https://openalex.org/W1567098080","https://openalex.org/W2550493152","https://openalex.org/W2345846362","https://openalex.org/W1578900076","https://openalex.org/W2294106860","https://openalex.org/W2517450235","https://openalex.org/W2051363478"],"abstract_inverted_index":{"We":[0,22],"present":[1],"a":[2,38,121],"computational":[3,137],"auditory":[4,138],"scene":[5,139],"analysis":[6],"system":[7],"for":[8,116],"separating":[9],"and":[10,43],"recognizing":[11],"target":[12,47],"speech":[13,19,122,135,145],"in":[14,24,37,71,111],"the":[15,27,35,46,51,54,57,65,90,99,130],"presence":[16],"of":[17,68],"competing":[18],"or":[20],"noise.":[21],"estimate,":[23],"two":[25],"stages,":[26],"ideal":[28],"binary":[29,141],"time-frequency":[30,142],"(T-F)":[31],"mask":[32],"which":[33],"retains":[34],"mixture":[36],"local":[39],"T-F":[40,100,107],"unit":[41],"if":[42,45],"only":[44],"is":[48],"stronger":[49],"than":[50],"interference":[52],"within":[53],"unit.":[55],"In":[56,89],"first":[58],"stage,":[59,92],"we":[60],"use":[61],"harmonicity":[62],"to":[63,97],"segregate":[64],"voiced":[66],"portions":[67,81],"individual":[69],"sources":[70],"each":[72],"time":[73,103],"frame":[74],"based":[75,84],"on":[76,85,120],"multipitch":[77],"tracking.":[78],"Additionally,":[79],"unvoiced":[80],"are":[82,95,109],"segmented":[83],"an":[86],"onset/offset":[87],"analysis.":[88],"second":[91],"speaker":[93],"characteristics":[94],"used":[96,110],"group":[98],"units":[101],"across":[102],"frames.":[104],"The":[105],"resulting":[106],"masks":[108],"conjunction":[112],"with":[113],"missing-data":[114],"methods":[115],"recognition.":[117,146],"Systematic":[118],"evaluations":[119],"separation":[123],"challenge":[124],"task":[125],"show":[126],"significant":[127],"improvement":[128],"over":[129],"baseline":[131],"performance.":[132],"Index":[133],"Terms:":[134],"segregation,":[136],"analysis,":[140],"mask,":[143],"robust":[144]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}