{"id":"https://openalex.org/W100896246","doi":"https://doi.org/10.21437/interspeech.2010-583","title":"Robust automatic speech recognition with decoder oriented ideal binary mask estimation","display_name":"Robust automatic speech recognition with decoder oriented ideal binary mask estimation","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W100896246","doi":"https://doi.org/10.21437/interspeech.2010-583","mag":"100896246"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-583","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5110266108","display_name":"Lae-Hoon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lae-Hoon Kim","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100295739","display_name":"Kyung-Tae Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyung-Tae Kim","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110266108"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.00736695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2066","last_page":"2069"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7044048309326172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.635529100894928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5163922905921936},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5127145051956177},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4896884262561798},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47910574078559875},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.46793362498283386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4674932062625885},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4661867022514343},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34728264808654785},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33904582262039185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22068753838539124},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.0754418671131134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044048309326172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.635529100894928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5163922905921936},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5127145051956177},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4896884262561798},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47910574078559875},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.46793362498283386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4674932062625885},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4661867022514343},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34728264808654785},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33904582262039185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22068753838539124},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0754418671131134},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-583","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.6040","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.6040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2010/kimlaehoon10interspeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2004372678","https://openalex.org/W2121973264","https://openalex.org/W2125838338","https://openalex.org/W2143855671","https://openalex.org/W2150866759","https://openalex.org/W2152131029","https://openalex.org/W2561557072","https://openalex.org/W2567948266","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W4317383455"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,27,43,62],"joint":[6],"optimal":[7],"method":[8,90],"for":[9],"automatic":[10],"speech":[11,123],"recognition":[12],"(ASR)":[13],"and":[14,50],"ideal":[15,125],"binary":[16,126],"mask":[17,127],"(IBM)":[18],"estimation":[19,58],"in":[20,78],"transformed":[21],"into":[22],"the":[23,48,70,88,115],"cepstral":[24,35,54],"domain":[25,36],"through":[26],"newly":[28],"derived":[29],"generalized":[30,63],"expectation":[31,64],"maximization":[32,65],"algorithm.":[33],"First,":[34],"missing":[37,129],"feature":[38,130],"marginalization":[39],"is":[40,59],"established":[41],"using":[42,61],"linear":[44],"transformation,":[45],"after":[46],"tying":[47],"mean":[49],"variance":[51],"of":[52],"non-existing":[53],"coefficients.":[55],"Second,":[56],"IBM":[57],"formulated":[60],"algorithm":[66],"directly":[67],"to":[68,106],"optimize":[69],"ASR":[71,95],"performance.":[72],"Experimental":[73],"results":[74],"show":[75],"that":[76],"even":[77],"highly":[79],"non-stationary":[80],"mismatch":[81],"condition":[82],"(dance":[83],"music":[84],"as":[85],"background":[86],"noise),":[87],"proposed":[89],"achieves":[91],"much":[92],"higher":[93],"absolute":[94],"accuracy":[96],"improvement":[97],"ranging":[98],"from":[99],"14.69":[100],"%":[101,108],"at":[102,109],"0":[103],"dB":[104,111],"SNR":[105,112],"40.10":[107],"15":[110],"compared":[113],"with":[114],"conventional":[116],"noise":[117],"suppression":[118],"method.":[119],"Index":[120],"Terms:":[121],"robust":[122],"recognition,":[124],"classification,":[128],"1.":[131]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}