{"id":"https://openalex.org/W2106259503","doi":"https://doi.org/10.1109/tasl.2010.2052610","title":"Robust Speech Recognition Based on Dereverberation Parameter Optimization Using Acoustic Model Likelihood","display_name":"Robust Speech Recognition Based on Dereverberation Parameter Optimization Using Acoustic Model Likelihood","publication_year":2010,"publication_date":"2010-06-16","ids":{"openalex":"https://openalex.org/W2106259503","doi":"https://doi.org/10.1109/tasl.2010.2052610","mag":"2106259503"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2052610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2052610","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2433/128840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["ACCMS, Kyoto University, Kyoto, Japan","ACCMS, Kyoto University, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACCMS, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"ACCMS, Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["ACCMS, Kyoto University, Kyoto, Japan","ACCMS, Kyoto University, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ACCMS, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"ACCMS, Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":4.0008,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94438337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"7","first_page":"1708","last_page":"1716"},"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":0.9991000294685364,"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":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.7718847990036011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.651660144329071},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5213326811790466},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.500873327255249},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.45574522018432617},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4533107876777649},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.428947389125824},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42703568935394287},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.4219318628311157},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35862040519714355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31866198778152466},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30750972032546997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11342796683311462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718847990036011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.651660144329071},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5213326811790466},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.500873327255249},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.45574522018432617},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4533107876777649},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.428947389125824},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42703568935394287},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.4219318628311157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35862040519714355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31866198778152466},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30750972032546997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11342796683311462},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2010.2052610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2052610","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000092853","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/128840","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000092853","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/128840","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1139504292","display_name":"Analysis and Generation of Speech Conversation by Considering Listener's Reaction","funder_award_id":"22240013","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W207188544","https://openalex.org/W1553270862","https://openalex.org/W1585936487","https://openalex.org/W1963844140","https://openalex.org/W2009106392","https://openalex.org/W2018228148","https://openalex.org/W2037740282","https://openalex.org/W2053241019","https://openalex.org/W2083212479","https://openalex.org/W2099036271","https://openalex.org/W2100969003","https://openalex.org/W2104690216","https://openalex.org/W2104924374","https://openalex.org/W2106119541","https://openalex.org/W2106553484","https://openalex.org/W2112197391","https://openalex.org/W2128653836","https://openalex.org/W2130640611","https://openalex.org/W2132214945","https://openalex.org/W2133908567","https://openalex.org/W2136883355","https://openalex.org/W2141418660","https://openalex.org/W2146871184","https://openalex.org/W2147542668","https://openalex.org/W2151046798","https://openalex.org/W2152949589","https://openalex.org/W2165935721","https://openalex.org/W2911394281","https://openalex.org/W2970850616","https://openalex.org/W2999905431","https://openalex.org/W4230562743","https://openalex.org/W6674532658","https://openalex.org/W6679561100","https://openalex.org/W6682371270","https://openalex.org/W6758139422"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W2154771632","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,28],"recognition":[2,88,148],"(ASR)":[3],"in":[4,41,59,147],"reverberant":[5,23],"environments":[6],"is":[7,80],"a":[8,35],"challenging":[9],"task.":[10],"Most":[11],"dereverberation":[12,40,57,120],"techniques":[13],"address":[14],"this":[15,31],"problem":[16],"through":[17],"signal":[18],"processing":[19],"and":[20,135],"enhances":[21],"the":[22,27,44,47,56,60,70,73,77,83,87,95,103,107,115,118,123,139,151,155],"waveform":[24],"independent":[25],"from":[26],"recognizer.":[29],"In":[30],"paper,":[32],"we":[33,90,113],"propose":[34],"novel":[36],"scheme":[37],"to":[38],"perform":[39],"relation":[42],"with":[43,150],"likelihood":[45,71],"of":[46,62,72,94,117],"back-end":[48],"ASR":[49],"system.":[50],"Our":[51],"proposed":[52,152],"approach":[53],"effectively":[54],"selects":[55],"parameters,":[58],"form":[61],"multiband":[63],"scale":[64,108],"factors,":[65],"so":[66],"that":[67],"they":[68],"improve":[69],"acoustic":[74,78,140],"model.":[75],"Then,":[76],"model":[79,101],"retrained":[81],"using":[82,98,130],"optimal":[84],"parameters.":[85,96],"During":[86],"phase,":[89],"implement":[91],"additional":[92],"optimization":[93],"By":[97],"Gaussian":[99],"mixture":[100],"(GMM),":[102],"process":[104],"for":[105],"selecting":[106,136],"factors":[109],"become":[110],"efficient.":[111],"Moreover,":[112],"remove":[114],"dependency":[116],"adopted":[119],"technique":[121],"on":[122,138],"room":[124],"impulse":[125],"response":[126],"(RIR)":[127],"measurement,":[128],"by":[129],"an":[131],"artificial":[132],"RIR":[133],"generator":[134],"based":[137],"likelihood.":[141],"Experimental":[142],"results":[143],"show":[144],"significant":[145],"improvement":[146],"performance":[149],"method":[153],"over":[154],"conventional":[156],"approach.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}