{"id":"https://openalex.org/W213902852","doi":"https://doi.org/10.21236/ada482069","title":"Monaural Speech Segregation by Integrating Primitive and Schema-Based Analysis","display_name":"Monaural Speech Segregation by Integrating Primitive and Schema-Based Analysis","publication_year":2008,"publication_date":"2008-02-03","ids":{"openalex":"https://openalex.org/W213902852","doi":"https://doi.org/10.21236/ada482069","mag":"213902852"},"language":"en","primary_location":{"id":"doi:10.21236/ada482069","doi":"https://doi.org/10.21236/ada482069","is_oa":false,"landing_page_url":"http://doi.org/10.21236/ada482069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"US Dept of the Air Force","raw_type":"report"},"volume":null,"type":"report","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","observed_orcids":["https://orcid.org/0000-0001-8195-6319"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053306339","display_name":"Nicoleta Roman","orcid":"https://orcid.org/0000-0001-9626-6329","observed_orcids":["https://orcid.org/0000-0001-9626-6329"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicoleta Roman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112457807","display_name":"Guoning Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoning Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045370151","display_name":"Soundar Srinivasan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soundar Srinivasan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406","observed_orcids":["https://orcid.org/0000-0002-4870-7406"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9473000168800354,"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":0.9473000168800354,"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":0.037300001829862595,"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":0.013100000098347664,"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/auditory-scene-analysis","display_name":"auditory scene analysis","score":0.9890000224113464},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"computational auditory scene analysis","score":0.8420000076293945},{"id":"https://openalex.org/keywords/phonemic-restoration","display_name":"phonemic restoration","score":0.925000011920929},{"id":"https://openalex.org/keywords/lexical-context","display_name":"lexical context","score":0.8769999742507935},{"id":"https://openalex.org/keywords/sequential-organization","display_name":"sequential organization","score":0.7860000133514404},{"id":"https://openalex.org/keywords/speaker-models","display_name":"speaker models","score":0.890999972820282},{"id":"https://openalex.org/keywords/event-detection","display_name":"event detection","score":0.9139999747276306},{"id":"https://openalex.org/keywords/pitch-estimation","display_name":"fundamental frequency estimation","score":0.8939999938011169},{"id":"https://openalex.org/keywords/voice-separation","display_name":"voice separation","score":0.9750000238418579}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8652095198631287},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6193143129348755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49223533272743225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4491075873374939},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.12211939692497253}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21236/ada482069","doi":"https://doi.org/10.21236/ada482069","is_oa":false,"landing_page_url":"http://doi.org/10.21236/ada482069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"US Dept of the Air Force","raw_type":"report"},{"id":"pmh:ADA482276","doi":null,"is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA482276","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W10765870","https://openalex.org/W2550493152","https://openalex.org/W244653749","https://openalex.org/W1977717807","https://openalex.org/W2373038971","https://openalex.org/W304408459","https://openalex.org/W2013312573","https://openalex.org/W2096496615","https://openalex.org/W4255513323","https://openalex.org/W2008592360"],"abstract_inverted_index":{"The":[0],"natural":[1],"auditory":[2,13,41,60,77,163,196],"environment":[3],"typically":[4],"contains":[5],"multiple":[6],"simultaneous":[7],"events.":[8],"A":[9,56,217],"remarkable":[10],"feat":[11],"of":[12,27,36,59,66,90,120,144,162,176,213,237,243,253],"perception":[14],"is":[15,39,63,148],"the":[16,20,25,28,87,91,93,100,117,121,142,174,251,254],"ability":[17],"to":[18,74,81,116,140,172],"disentangle":[19],"acoustic":[21],"mixture":[22],"and":[23,51,211,228],"group":[24],"components":[26],"same":[29],"event":[30,167],"into":[31],"a":[32,47,52,108,183,190,235],"stream.":[33],"This":[34,71],"aspect":[35],"human":[37],"audition":[38],"called":[40],"scene":[42,61,78,197],"analysis":[43,62,79,198],"(ASA),":[44],"which":[45,114,147],"has":[46,95,204,231],"primitive":[48],"(bottom-up)":[49],"process":[50],"schema-based":[53,109],"(top-down)":[54],"process.":[55],"major":[57],"task":[58],"monaural":[64,82],"segregation":[65,175],"speech":[67,83,210,215],"from":[68],"interfering":[69],"sounds.":[70],"project":[72,94],"seeks":[73],"develop":[75],"an":[76,138,158,170],"approach":[80,139,159],"segregation.":[84],"Consistent":[85],"with":[86],"stated":[88],"objectives":[89],"project,":[92],"made":[96,206],"considerable":[97],"progress":[98,203],"along":[99],"following":[101],"four":[102],"directions.":[103],"First,":[104],"we":[105,135,155,180],"have":[106,136,156,181],"proposed":[107,157],"model":[110],"for":[111,160,186,224],"phonemic":[112],"restoration,":[113],"refers":[115],"perceptual":[118],"synthesis":[119],"phonemes":[122],"that":[123],"are":[124],"masked":[125],"by":[126,130],"appropriate":[127],"replacement":[128],"sounds":[129],"utilizing":[131],"lexical":[132],"context.":[133],"Second,":[134],"developed":[137,182],"address":[141,173],"problem":[143],"sequential":[145],"organization,":[146],"based":[149,165],"on":[150,166,207],"trained":[151],"speaker":[152],"models.":[153],"Third,":[154],"segmentation":[161],"scenes":[164],"detection,":[168],"in":[169,194],"attempt":[171],"unvoiced":[177,188],"speech.":[178],"Fourth,":[179],"comprehensive":[184],"system":[185],"segregating":[187],"speech,":[189],"long":[191],"standing":[192],"challenge":[193],"computational":[195],"(CASA).":[199],"In":[200],"addition,":[201],"encouraging":[202],"been":[205,232],"enhancing":[208],"reverberant":[209],"modeling":[212],"multitalker":[214],"perception.":[216],"provisional":[218],"patent":[219],"application":[220],"entitled":[221],"\"A":[222],"method":[223],"accurate":[225],"pitch":[226],"estimation":[227],"voice":[229],"separation,\"":[230],"filed":[233],"as":[234],"result":[236],"this":[238],"AFOSR":[239],"grant.":[240],"Executive":[241],"summaries":[242],"doctoral":[244],"dissertations":[245],"supported":[246],"can":[247],"be":[248],"found":[249],"at":[250],"back":[252],"reports.":[255]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}