{"id":"https://openalex.org/W2396825535","doi":"https://doi.org/10.21437/interspeech.2011-618","title":"Adaptive stream fusion in multistream recognition of speech","display_name":"Adaptive stream fusion in multistream recognition of speech","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2396825535","doi":"https://doi.org/10.21437/interspeech.2011-618","mag":"2396825535"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-618","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033351155"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4956,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90571931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2329","last_page":"2332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9983000159263611,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.735404908657074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7055306434631348},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49621230363845825},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4934212267398834},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48720473051071167},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4220956265926361},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.42096197605133057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3970944881439209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735404908657074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7055306434631348},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49621230363845825},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4934212267398834},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48720473051071167},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4220956265926361},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.42096197605133057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3970944881439209},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":2,"locations":[{"id":"doi:10.21437/interspeech.2011-618","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.226.9384","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.9384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/adaptive_multistream.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W86999225","https://openalex.org/W96431220","https://openalex.org/W1553004968","https://openalex.org/W1571573569","https://openalex.org/W1802969839","https://openalex.org/W1920478749","https://openalex.org/W1994139191","https://openalex.org/W1997560282","https://openalex.org/W2025192094","https://openalex.org/W2054139811","https://openalex.org/W2090861223","https://openalex.org/W2096215262","https://openalex.org/W2113952909","https://openalex.org/W2153723410","https://openalex.org/W2160337655"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W2152662039","https://openalex.org/W2129377384","https://openalex.org/W2362031592","https://openalex.org/W2356580463","https://openalex.org/W2981428355","https://openalex.org/W1834994814"],"abstract_inverted_index":{"A":[0,75],"new":[1],"method":[2],"to":[3,42,86,105],"deal":[4],"with":[5,66],"variable":[6],"distortions":[7],"of":[8,13,46,54,63,78,119],"speech":[9,34,115,126],"during":[10],"the":[11,14,33,64,67,72,79,88,92,94,97,107,117,120],"operation":[12],"system":[15,89],"is":[16,40,84],"proposed.":[17],"First,":[18],"multiple":[19],"processing":[20],"streams":[21],"are":[22,58,100],"formed":[23],"by":[24,60],"extracting":[25],"different":[26],"spectral":[27],"and":[28],"temporal":[29],"modulation":[30],"components":[31],"from":[32,113],"signal.":[35],"Information":[36],"in":[37,96],"each":[38],"stream":[39],"used":[41,85],"estimate":[43],"posterior":[44,82],"probabilities":[45,83],"phonemes.":[47],"Initial":[48],"values":[49],"for":[50],"a":[51],"weighted":[52],"integration":[53],"these":[55],"individual":[56],"estimates":[57,65],"found":[59],"normalized":[61],"cross-correlation":[62],"actual":[68],"phoneme":[69,111],"labels":[70],"on":[71,110],"training":[73],"data.":[74],"statistical":[76],"model":[77],"final":[80],"estimated":[81],"characterize":[87],"performance.":[90,108],"During":[91],"operation,":[93],"weights":[95],"linear":[98],"fusion":[99],"adapted":[101],"using":[102],"particle":[103],"filtering":[104],"optimize":[106],"Results":[109],"recognition":[112],"noisy":[114],"indicate":[116],"effectiveness":[118],"proposed":[121],"method.":[122],"Index":[123],"Terms:":[124],"multistream":[125],"recognition,":[127],"spectrotemporal":[128],"modulations":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}