{"id":"https://openalex.org/W2139062922","doi":"https://doi.org/10.1109/icassp.2005.1415057","title":"Robust Speech Recognition by Integrating Speech Separation and Hypothesis Testing","display_name":"Robust Speech Recognition by Integrating Speech Separation and Hypothesis Testing","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2139062922","doi":"https://doi.org/10.1109/icassp.2005.1415057","mag":"2139062922"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415057","doi":"https://doi.org/10.1109/icassp.2005.1415057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415057","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"volume":null,"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/A5103115230","display_name":"Swaminathan Srinivasan","orcid":"https://orcid.org/0000-0002-4919-215X","observed_orcids":["https://orcid.org/0000-0002-4919-215X"]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Srinivasan","raw_affiliation_strings":["Biomedical Engineering Center, Ohio State Uinversity, Columbus, OH, USA","Biomed. Eng. Center, Ohio State Univ., Columbus, OH, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Engineering Center, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Biomed. Eng. Center, Ohio State Univ., Columbus, OH, USA#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319","observed_orcids":["https://orcid.org/0000-0001-8195-6319"]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science & Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering and Center for Cognitive Science, The Ohio State University, Columbus, OH 43210, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and Center for Cognitive Science, The Ohio State University, Columbus, OH 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.7189,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69368344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"89","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8711000084877014,"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":0.8711000084877014,"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":0.12809999287128448,"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":0.00019999999494757503,"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/robust-speech-recognition","display_name":"robust speech recognition","score":0.9919999837875366},{"id":"https://openalex.org/keywords/speech-separation","display_name":"speech separation","score":0.8399999737739563},{"id":"https://openalex.org/keywords/hypothesis-testing","display_name":"hypothesis testing","score":0.7379999756813049},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.6299999952316284},{"id":"https://openalex.org/keywords/time-frequency-masking","display_name":"time-frequency masking","score":0.6420000195503235},{"id":"https://openalex.org/keywords/lattice-rescoring","display_name":"lattice rescoring","score":0.9179999828338623},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.5509999990463257},{"id":"https://openalex.org/keywords/bottom-up-cues","display_name":"bottom-up cues","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775882482528687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7544057369232178},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5170577168464661},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5063084363937378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47544407844543457},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4724850058555603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.469806969165802},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42916256189346313},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4291518032550812},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4279389977455139},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.42605292797088623},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4218358099460602},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4173651933670044},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15403690934181213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0959877073764801},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415057","doi":"https://doi.org/10.1109/icassp.2005.1415057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415057","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W147991855","https://openalex.org/W169161303","https://openalex.org/W1542258417","https://openalex.org/W1566344028","https://openalex.org/W1575829986","https://openalex.org/W1592635802","https://openalex.org/W1637294163","https://openalex.org/W1800365115","https://openalex.org/W1974387177","https://openalex.org/W1974556460","https://openalex.org/W1992402718","https://openalex.org/W2003869208","https://openalex.org/W2016254085","https://openalex.org/W2034040413","https://openalex.org/W2045036776","https://openalex.org/W2074354966","https://openalex.org/W2080921589","https://openalex.org/W2086139506","https://openalex.org/W2095345875","https://openalex.org/W2097191389","https://openalex.org/W2106603795","https://openalex.org/W2123098109","https://openalex.org/W2128202590","https://openalex.org/W2128653836","https://openalex.org/W2134958651","https://openalex.org/W2148154194","https://openalex.org/W2149425615","https://openalex.org/W2149693148","https://openalex.org/W2151484683","https://openalex.org/W2152131029","https://openalex.org/W2281646695","https://openalex.org/W2561557072","https://openalex.org/W2981666567","https://openalex.org/W3216401400","https://openalex.org/W4256399001"],"related_works":["https://openalex.org/W2111835153","https://openalex.org/W2164388284","https://openalex.org/W2041403384","https://openalex.org/W2135854294","https://openalex.org/W2147442641","https://openalex.org/W2134162816","https://openalex.org/W2010377246","https://openalex.org/W169161303","https://openalex.org/W2005894366","https://openalex.org/W2134958651"],"abstract_inverted_index":{"Missing":[0],"data":[1,15],"methods":[2,21,50],"attempt":[3],"to":[4,86,121,138],"improve":[5,87],"robust":[6],"speech":[7,33,41,60,102,141],"recognition":[8,75,82,93,135],"by":[9,112],"distinguishing":[10],"between":[11],"reliable":[12,36],"and":[13,46,66,90],"unreliable":[14,47],"in":[16,74,84,134],"the":[17,53,101,114,123],"time-frequency":[18,28,127],"domain.":[19],"Such":[20],"require":[22],"a":[23,31,72,79,117],"binary":[24],"mask":[25,54,88,104,115],"which":[26],"labels":[27],"regions":[29],"of":[30,125],"noisy":[32],"signal":[34],"as":[35,64],"if":[37],"they":[38],"contain":[39],"more":[40],"energy":[42,45],"than":[43],"noise":[44],"otherwise.":[48],"Current":[49],"for":[51],"estimating":[52],"are":[55],"based":[56],"mainly":[57],"on":[58],"bottom-up":[59],"separation":[61,103],"cues":[62],"such":[63],"harmonicity":[65],"produce":[67,91],"labeling":[68],"errors":[69],"that":[70,139],"cause":[71],"degradation":[73],"performance.":[76],"We":[77],"propose":[78],"two":[80],"stage":[81],"system":[83],"order":[85],"estimation":[89],"better":[92],"results.":[94],"First,":[95],"an":[96],"n-best":[97],"lattice":[98,108],"consistent":[99],"with":[100],"is":[105,109],"generated.":[106],"The":[107],"then":[110],"re-scored":[111],"expanding":[113],"using":[116,140],"model-based":[118],"hypothesis":[119],"test":[120],"determine":[122],"reliability":[124],"individual":[126],"regions.":[128],"Systematic":[129],"evaluations":[130],"show":[131],"significant":[132],"improvement":[133],"performance":[136],"compared":[137],"separation.":[142]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}