{"id":"https://openalex.org/W2159675447","doi":"https://doi.org/10.1109/icassp.2011.5947599","title":"Maximum likelihood adaptation of histogram equalization with constraint for robust speech recognition","display_name":"Maximum likelihood adaptation of histogram equalization with constraint for robust speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2159675447","doi":"https://doi.org/10.1109/icassp.2011.5947599","mag":"2159675447"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Human Language Technology, Institute for Infocomm Research, Singapore","School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Human Language Technology, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101602536"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.5655,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90836097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":null,"first_page":"5480","last_page":"5483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9969000220298767,"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/robustness","display_name":"Robustness (evolution)","score":0.7083491086959839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5842185616493225},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.5782383680343628},{"id":"https://openalex.org/keywords/histogram-equalization","display_name":"Histogram equalization","score":0.5525951385498047},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5007839202880859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4855465590953827},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4361552894115448},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4250045418739319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3444981575012207}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7083491086959839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5842185616493225},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.5782383680343628},{"id":"https://openalex.org/C136943445","wikidata":"https://www.wikidata.org/wiki/Q1970240","display_name":"Histogram equalization","level":4,"score":0.5525951385498047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5007839202880859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4855465590953827},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4361552894115448},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4250045418739319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3444981575012207},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"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/W1488465960","https://openalex.org/W2007199174","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2099881084","https://openalex.org/W2100969003","https://openalex.org/W2106714211","https://openalex.org/W2115515280","https://openalex.org/W2120605154","https://openalex.org/W2137401359","https://openalex.org/W2146871184","https://openalex.org/W2151484683","https://openalex.org/W2152175514","https://openalex.org/W2171000037","https://openalex.org/W6680646222"],"related_works":["https://openalex.org/W2057981026","https://openalex.org/W2256021896","https://openalex.org/W2181573213","https://openalex.org/W2398368608","https://openalex.org/W1990492110","https://openalex.org/W1583737874","https://openalex.org/W2122866860","https://openalex.org/W2024449420","https://openalex.org/W2903465195","https://openalex.org/W2380937280"],"abstract_inverted_index":{"In":[0,66,93],"this":[1,67,116],"paper,":[2,68],"we":[3,69,95],"propose":[4,70],"a":[5,86,97],"novel":[6],"feature":[7,106],"space":[8,107],"adaptation":[9,131],"technique":[10,27],"to":[11,71,74,102],"improve":[12],"the":[13,33,63,76,82,89,104,111,147],"robustness":[14,30],"of":[15,42,78,91],"speech":[16],"recognition":[17],"in":[18,55,118],"noisy":[19,38],"environments.":[20],"Histogram":[21],"equalization":[22],"(HEQ)":[23],"is":[24,44],"an":[25],"effective":[26],"for":[28],"improving":[29],"by":[31,136],"reducing":[32],"difference":[34],"between":[35,58],"clean":[36,105],"and":[37,62,115,122,138,143],"features.":[39],"A":[40],"weakness":[41],"HEQ":[43,59,73,129,148],"that":[45,128],"it":[46],"does":[47],"not":[48],"take":[49],"into":[50],"account":[51],"acoustic":[52,64,83,112],"model,":[53,84],"resulting":[54],"possible":[56],"mismatch":[57],"processed":[60],"features":[61,80],"model.":[65],"adapt":[72],"maximize":[75],"likelihood":[77],"HEQ-processed":[79],"on":[81,88,141],"with":[85,130],"constraint":[87],"parameters":[90],"HEQ.":[92],"addition,":[94],"use":[96],"Gaussian":[98],"mixture":[99],"model":[100,113],"(GMM)":[101],"represent":[103],"rather":[108],"than":[109],"using":[110],"itself,":[114],"results":[117,126],"both":[119],"simpler":[120],"implementation":[121],"better":[123],"results.":[124],"Experimental":[125],"show":[127],"reduces":[132],"word":[133],"error":[134],"rate":[135],"7.5%":[137],"5.7%":[139],"respectively":[140],"Aurora-2":[142],"Aurora-4":[144],"tasks":[145],"over":[146],"baseline":[149],"without":[150],"adaptation.":[151]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}