{"id":"https://openalex.org/W304408459","doi":"https://doi.org/10.21236/ada567198","title":"Sequential Organization and Room Reverberation for Speech Segregation","display_name":"Sequential Organization and Room Reverberation for Speech Segregation","publication_year":2012,"publication_date":"2012-02-28","ids":{"openalex":"https://openalex.org/W304408459","doi":"https://doi.org/10.21236/ada567198","mag":"304408459"},"language":"en","primary_location":{"id":"doi:10.21236/ada567198","doi":"https://doi.org/10.21236/ada567198","is_oa":false,"landing_page_url":"https://doi.org/10.21236/ada567198","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":true,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051837453"],"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":0.9976000189781189,"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":0.9976000189781189,"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":0.0010000000474974513,"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":0.0010000000474974513,"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/speech-segregation","display_name":"speech segregation","score":0.8450000286102295},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"auditory scene analysis","score":0.9800000190734863},{"id":"https://openalex.org/keywords/sequential-organization","display_name":"sequential organization","score":0.7549999952316284},{"id":"https://openalex.org/keywords/room-reverberation","display_name":"room reverberation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/pitch-tracking","display_name":"pitch tracking","score":0.8460000157356262},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.8220000267028809},{"id":"https://openalex.org/keywords/binary-masking","display_name":"binary masking","score":0.8299999833106995},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.9279999732971191},{"id":"https://openalex.org/keywords/speech-recognition-in-noise","display_name":"speech recognition in noise","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8772194981575012},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8207346796989441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7711629271507263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382041215896606},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.655007004737854},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5859535336494446},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5196179747581482},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.450990229845047},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42930975556373596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3538007438182831},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34902164340019226},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16419854760169983},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21236/ada567198","doi":"https://doi.org/10.21236/ada567198","is_oa":false,"landing_page_url":"https://doi.org/10.21236/ada567198","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"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2602116303","https://openalex.org/W2096496615","https://openalex.org/W2213640299","https://openalex.org/W2142909779","https://openalex.org/W2152632599","https://openalex.org/W2401269416","https://openalex.org/W2111893856","https://openalex.org/W2098189132","https://openalex.org/W2752834270","https://openalex.org/W2013312573"],"abstract_inverted_index":{"Abstract":[0],":":[1],"Inspired":[2],"by":[3,104],"the":[4,47,160],"perceptual":[5],"account":[6],"of":[7,89,162],"auditory":[8],"scene":[9],"analysis,":[10],"significant":[11],"advances":[12],"were":[13,125,153],"made":[14,45],"in":[15,18,81,92,170],"speech":[16,62,91,102,108,116,150,168],"segregation":[17,63,88,103],"recent":[19],"years.":[20],"Despite":[21],"these":[22,38],"advances,":[23],"two":[24,39],"major":[25],"challenges":[26],"remained:":[27],"sequential":[28,128],"organization":[29],"and":[30,60,74,109,112,138,145,155],"room":[31],"reverberation.":[32],"This":[33],"project":[34],"aimed":[35],"to":[36,87,135],"address":[37],"challenges.":[40],"Substantial":[41],"progress":[42],"has":[43],"been":[44],"along":[46],"following":[48],"directions.":[49],"First":[50],"a":[51,66,82,96,139],"tandem":[52],"algorithm":[53,69,133,141],"was":[54,70,78,98],"developed":[55],"that":[56,142],"performs":[57],"pitch":[58],"tracking":[59,68],"voiced":[61,90,107],"iteratively.":[64],"Second,":[65],"multipitch":[67],"proposed":[71,126],"for":[72,100,127,165],"noisy":[73,171],"reverberant":[75,93],"speech,":[76],"which":[77],"then":[79,113],"used":[80],"novel,":[83],"supervised":[84],"learning":[85],"approach":[86],"environments.":[94],"Third,":[95],"method":[97],"suggested":[99],"unvoiced":[101,115],"first":[105],"removing":[106],"periodic":[110],"components,":[111],"grouping":[114],"segments":[117],"through":[118],"analyzing":[119],"their":[120,156],"spectral":[121],"characteristics.":[122],"Two":[123],"algorithms":[124],"organization,":[129],"an":[130],"unsupervised":[131],"clustering":[132],"applicable":[134],"monaural":[136,144],"recordings":[137],"binaural":[140,146],"integrates":[143],"analyses.":[147],"In":[148],"addition,":[149],"intelligibility":[151],"tests":[152],"conducted":[154],"results":[157],"firmly":[158],"establish":[159],"effectiveness":[161],"binary":[163],"masking":[164],"improving":[166],"human":[167],"recognition":[169],"backgrounds.":[172]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2016-06-24T00:00:00"}
