{"id":"https://openalex.org/W2085999026","doi":"https://doi.org/10.1109/aspaa.2011.6082294","title":"On the combination of voice prompt suppression with maximum kurtosis beamforming","display_name":"On the combination of voice prompt suppression with maximum kurtosis beamforming","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2085999026","doi":"https://doi.org/10.1109/aspaa.2011.6082294","mag":"2085999026"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5106034394","display_name":"John McDonough","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":true,"raw_author_name":"John McDonough","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University, Gates-Hillman Complex, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Gates-Hillman Complex, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","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":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University, Gates-Hillman Complex, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Gates-Hillman Complex, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915317","display_name":"Kenichi Kumatani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenichi Kumatani","raw_affiliation_strings":["Disney Research, Pittsburgh, Pittsburgh, PA, USA","Disney Research, Pittsburgh, 4720 Forbes Avenue, Lower Level, Suite 110, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210142140"]},{"raw_affiliation_string":"Disney Research, Pittsburgh, 4720 Forbes Avenue, Lower Level, Suite 110, PA 15213, USA","institution_ids":["https://openalex.org/I4210142140"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106034394"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67428237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"28"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.7069921493530273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6523941159248352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6254282593727112},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6233277916908264},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5920692086219788},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.550630509853363},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5014979839324951},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.4884189963340759},{"id":"https://openalex.org/keywords/kurtosis","display_name":"Kurtosis","score":0.46952977776527405},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46384432911872864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2766134440898895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24330604076385498},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1683548092842102},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09780663251876831},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.08695343136787415}],"concepts":[{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.7069921493530273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523941159248352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6254282593727112},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6233277916908264},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5920692086219788},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.550630509853363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5014979839324951},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4884189963340759},{"id":"https://openalex.org/C166963901","wikidata":"https://www.wikidata.org/wiki/Q287251","display_name":"Kurtosis","level":2,"score":0.46952977776527405},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46384432911872864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2766134440898895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24330604076385498},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1683548092842102},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09780663251876831},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.08695343136787415},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/aspaa.2011.6082294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.4492","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.4492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lsv.uni-saarland.de/personalPages/kkumatani/pubdata/Wasspa2011a.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.365.8208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.365.8208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mlsp.cs.cmu.edu/publications/pdfs/McDonough-WASPAA2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W87496662","https://openalex.org/W1537786506","https://openalex.org/W2000350385","https://openalex.org/W2039893359","https://openalex.org/W2544665648","https://openalex.org/W2790374560","https://openalex.org/W4206633762","https://openalex.org/W6660404295"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W2107649022","https://openalex.org/W3123211304","https://openalex.org/W3149332717","https://openalex.org/W2768858086","https://openalex.org/W4327750154","https://openalex.org/W3172690770"],"abstract_inverted_index":{"In":[0,59,124],"earlier":[1,65],"work,":[2,61],"we":[3,62,132],"proposed":[4],"a":[5,13,69,82,125,155],"voice":[6],"prompt":[7],"suppression":[8],"(VPS)":[9],"algorithm":[10],"based":[11],"on":[12],"Kalman":[14],"filter,":[15],"in":[16,26,43,96],"which":[17,54,111],"the":[18,36,47,50,74,87,91,102],"temporal":[19],"update":[20],"or":[21],"correction":[22],"step":[23],"is":[24,34],"performed":[25],"information":[27,37,75],"space.":[28],"The":[29],"advantage":[30],"of":[31,49,73,90,104,127],"this":[32,60,97],"approach":[33],"that":[35,64,134],"matrix":[38,94],"can":[39,136],"be":[40],"diagonally":[41,85],"loaded":[42],"order":[44],"to":[45,115,119,143,152],"control":[46],"magnitude":[48],"subband":[51],"filter":[52,76],"coefficients,":[53],"provides":[55],"for":[56,84,145,154],"better":[57],"robustness.":[58],"extend":[63],"work":[66],"by":[67],"proposing":[68],"square":[70],"root":[71],"implementation":[72],"VPS":[77,106,135],"algorithm,":[78],"as":[79,81],"well":[80],"technique":[83],"loading":[86],"Cholesky":[88],"factor":[89],"error":[92,139],"covariance":[93],"used":[95],"implementation.":[98],"We":[99],"also":[100],"investigate":[101],"effectiveness":[103],"cascading":[105],"after":[107],"maximum":[108],"kurtosis":[109],"beamforming,":[110],"has":[112],"been":[113],"shown":[114],"provide":[116],"performance":[117],"superior":[118],"all":[120],"conventional":[121],"beamforming":[122],"techniques.":[123],"set":[126],"distant":[128],"speech":[129],"recognition":[130],"experiments":[131],"demonstrate":[133],"reduce":[137],"word":[138],"rate":[140],"from":[141,150],"19.9%":[142],"16.1%":[144],"an":[146],"adult":[147],"speaker,":[148],"and":[149],"44.4%":[151],"40.0%":[153],"child.":[156]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}