{"id":"https://openalex.org/W2162309976","doi":"https://doi.org/10.1109/icassp.2012.6288968","title":"A comparison of front-end compensation strategies for robust LVCSR under room reverberation and increased vocal effort","display_name":"A comparison of front-end compensation strategies for robust LVCSR under room reverberation and increased vocal effort","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2162309976","doi":"https://doi.org/10.1109/icassp.2012.6288968","mag":"2162309976"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288968","doi":"https://doi.org/10.1109/icassp.2012.6288968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288968","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":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5051167459","display_name":"Seyed Omid Sadjadi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Omid Sadjadi","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009895165","display_name":"Hynek Bo\u0159il","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Boril","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.472,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83472138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4701","last_page":"4704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.9932000041007996,"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":0.0066999997943639755,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-vocabulary-continuous-speech-recognition","display_name":"large vocabulary continuous speech recognition","score":0.9079999923706055},{"id":"https://openalex.org/keywords/room-reverberation","display_name":"room reverberation","score":0.9440000057220459},{"id":"https://openalex.org/keywords/front-end-feature-extraction","display_name":"front-end feature extraction","score":0.8190000057220459},{"id":"https://openalex.org/keywords/feature-normalization","display_name":"feature normalization","score":0.7839999794960022},{"id":"https://openalex.org/keywords/robust-speech-recognition","display_name":"robust speech recognition","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7883913516998291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465344071388245},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6820383071899414},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6425542831420898},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5724796056747437},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47075560688972473},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4617566764354706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3049357831478119},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23750340938568115},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288968","doi":"https://doi.org/10.1109/icassp.2012.6288968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288968","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":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.545","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.utdallas.edu/~hynek/pdfs/SadjadiBoril_ICASSP12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W54525843","https://openalex.org/W1230632900","https://openalex.org/W1986916617","https://openalex.org/W2004826498","https://openalex.org/W2072328708","https://openalex.org/W2078020518","https://openalex.org/W2088744964","https://openalex.org/W2097491464","https://openalex.org/W2108661465","https://openalex.org/W2110322414","https://openalex.org/W2114782757","https://openalex.org/W2117486215","https://openalex.org/W2121892718","https://openalex.org/W2127057679","https://openalex.org/W2129741985","https://openalex.org/W2136682440","https://openalex.org/W2137075158","https://openalex.org/W2145692202","https://openalex.org/W2155082225","https://openalex.org/W2188162373","https://openalex.org/W2397634864","https://openalex.org/W2405895519"],"related_works":["https://openalex.org/W7097241483","https://openalex.org/W2405895519","https://openalex.org/W1820182450","https://openalex.org/W292344134","https://openalex.org/W246278971","https://openalex.org/W148193739","https://openalex.org/W2909568402","https://openalex.org/W2612815004","https://openalex.org/W2097491464","https://openalex.org/W2108327698"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,37,47,51,60,62],"recognition":[2,48,112],"is":[3,70,83],"known":[4],"to":[5,33],"deteriorate":[6],"in":[7,18,40,54,79],"the":[8,41,80,86],"presence":[9],"of":[10,15,24,36,43,67,88],"room":[11,74],"reverberation":[12],"and":[13,30,61,77,96,104,118],"variation":[14],"vocal":[16,68,120],"effort":[17,121],"speakers.":[19],"This":[20],"study":[21],"considers":[22],"robustness":[23],"several":[25],"state-of-the-art":[26],"front-end":[27],"feature":[28],"extraction":[29],"normalization":[31,98,103],"strategies":[32],"these":[34],"sources":[35],"signal":[38],"variability":[39],"context":[42],"large":[44],"vocabulary":[45],"continuous":[46],"(LVCSR).":[49],"A":[50],"database":[52],"recorded":[53],"an":[55],"anechoic":[56],"room,":[57],"capturing":[58],"modal":[59,117],"produced":[63],"at":[64],"different":[65],"levels":[66],"effort,":[69],"reverberated":[71],"using":[72],"measured":[73],"impulse":[75],"responses":[76],"utilized":[78],"evaluations.":[81],"It":[82],"shown":[84],"that":[85],"combination":[87],"recently":[89],"introduced":[90],"mean":[91],"Hilbert":[92],"envelope":[93],"coefficients":[94],"(MHEC)":[95],"a":[97],"strategy":[99],"combining":[100],"cepstral":[101],"gain":[102],"modified":[105],"RASTA":[106],"filtering":[107],"(CGN":[108],"RASTALP)":[109],"provides":[110],"considerable":[111],"performance":[113],"gains":[114],"for":[115],"reverberant":[116],"high":[119],"speech.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}