{"id":"https://openalex.org/W2109417541","doi":"https://doi.org/10.1109/icassp.1996.543266","title":"Microphone-array speech recognition via incremental map training","display_name":"Microphone-array speech recognition via incremental map training","publication_year":2002,"publication_date":"2002-12-23","ids":{"openalex":"https://openalex.org/W2109417541","doi":"https://doi.org/10.1109/icassp.1996.543266","mag":"2109417541"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1996.543266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.543266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","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/A5019203445","display_name":"John Adcock","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.E. Adcock","raw_affiliation_strings":["LEMS, Division of Engineering, Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEMS, Division of Engineering, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047046960","display_name":"Yoshihiko Gotoh","orcid":"https://orcid.org/0000-0003-1668-0867"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Gotoh","raw_affiliation_strings":["LEMS, Division of Engineering, Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEMS, Division of Engineering, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009285575","display_name":"Daniel Mashao","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.j. Mashao","raw_affiliation_strings":["LEMS, Division of Engineering, Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEMS, Division of Engineering, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113228448","display_name":"H.F. Silverman","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H.F. Silverman","raw_affiliation_strings":["LEMS, Division of Engineering, Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LEMS, Division of Engineering, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":2.2023,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.88821567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"897","last_page":"900"},"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":0.9991999864578247,"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":0.9987000226974487,"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/speech-recognition","display_name":"Speech recognition","score":0.796341061592102},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7748916149139404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7737313508987427},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.672684371471405},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6670299172401428},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5739613175392151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5344672799110413},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5306673645973206},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5127914547920227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47242701053619385},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4348088502883911},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1775699257850647},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.10475146770477295},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10467004776000977}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.796341061592102},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7748916149139404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737313508987427},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.672684371471405},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6670299172401428},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5739613175392151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5344672799110413},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5306673645973206},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5127914547920227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47242701053619385},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4348088502883911},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1775699257850647},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.10475146770477295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10467004776000977},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.1996.543266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.543266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.30.8328","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.30.8328","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/~yg/./papers_ps2/atlanta2.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1561818904","https://openalex.org/W1721259867","https://openalex.org/W1902863935","https://openalex.org/W1997130789","https://openalex.org/W2031917210","https://openalex.org/W2037769258","https://openalex.org/W2045352743","https://openalex.org/W2049633694","https://openalex.org/W2063089147","https://openalex.org/W2080135598","https://openalex.org/W2100969003","https://openalex.org/W2114044590","https://openalex.org/W2128653836","https://openalex.org/W2130432819","https://openalex.org/W3129711340","https://openalex.org/W4247773827","https://openalex.org/W6666220839","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W1595191759","https://openalex.org/W1879255185","https://openalex.org/W2010299594","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2396048001","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2348931051"],"abstract_inverted_index":{"For":[0],"a":[1,28,46,57,70,77,84,91,95],"hidden":[2],"Markov":[3],"model":[4,24,87],"(HMM)":[5],"based":[6],"speech":[7,31,60,66,79],"recognition":[8,61,80,112],"system":[9,62,93],"it":[10],"is":[11,50,74,88],"desirable":[12],"to":[13,52,63,115],"combine":[14],"enhancement":[15,122,125],"of":[16,23,44,56,99],"the":[17,41,54,116,129],"acoustical":[18],"signal":[19,32,121],"and":[20,33,118,127],"statistical":[21],"representation":[22],"parameters,":[25],"ensuring":[26],"both":[27],"high":[29],"quality":[30],"an":[34],"appropriately":[35],"trained":[36],"HMM.":[37],"In":[38],"this":[39],"paper":[40],"incremental":[42],"variant":[43],"maximum":[45],"posteriori":[47],"(MAP)":[48],"estimation":[49],"used":[51],"adjust":[53],"parameters":[55],"talker-independent":[58,86],"HMM-based":[59],"accurately":[64],"recognize":[65],"data":[67,100],"acquired":[68],"with":[69],"microphone-array.":[71],"The":[72,103],"approach":[73],"novel":[75],"for":[76,101],"microphone-array":[78],"task":[81],"in":[82],"that":[83,106],"robust":[85],"derived":[89],"from":[90],"baseline":[92],"using":[94],"relatively":[96],"small":[97],"amount":[98],"training.":[102,132],"results":[104],"show":[105],"(1)":[107],"ILIAP":[108],"training":[109],"significantly":[110],"improves":[111],"performance":[113],"compared":[114],"baseline,":[117],"(2)":[119],"beamforming":[120],"outperforms":[123],"single-channel":[124],"before":[126],"after":[128],"adaptive":[130],"MAP":[131]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}