{"id":"https://openalex.org/W2403157797","doi":"https://doi.org/10.21437/interspeech.2011-211","title":"Feature compensation for speech recognition in severely adverse environments due to background noise and channel distortion","display_name":"Feature compensation for speech recognition in severely adverse environments due to background noise and channel distortion","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2403157797","doi":"https://doi.org/10.21437/interspeech.2011-211","mag":"2403157797"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-211","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5101977970","display_name":"Wooil Kim","orcid":"https://orcid.org/0000-0002-3854-2783"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wooil Kim","raw_affiliation_strings":["University of Texas at Dallas"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101977970"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33215783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1653","last_page":"1656"},"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":0.9998000264167786,"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/speech-recognition","display_name":"Speech recognition","score":0.7857459783554077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749282121658325},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7649098038673401},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5968072414398193},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5902716517448425},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5169872045516968},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4880284368991852},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4747526943683624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4688739776611328},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4676154851913452},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4212411642074585},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.412988543510437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4124009609222412},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16301870346069336},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06424647569656372}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7857459783554077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749282121658325},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7649098038673401},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5968072414398193},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5902716517448425},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5169872045516968},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4880284368991852},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4747526943683624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4688739776611328},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4676154851913452},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4212411642074585},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.412988543510437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4124009609222412},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16301870346069336},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06424647569656372},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2011-211","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W79317937","https://openalex.org/W1586084638","https://openalex.org/W1665196592","https://openalex.org/W2045036776","https://openalex.org/W2100969003","https://openalex.org/W2114992418","https://openalex.org/W2144404214","https://openalex.org/W2146871184","https://openalex.org/W2151484683","https://openalex.org/W2162213734"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"effective":[4,121],"feature":[5,45,116,149],"compensation":[6,46,117],"scheme":[7,118],"to":[8,137],"address":[9],"severely":[10],"adverse":[11],"environments":[12],"for":[13,98],"robust":[14,154],"speech":[15,51,78,85,91,99,110,124,155],"recognition,":[16],"where":[17],"background":[18,131],"noise":[19,61,132],"and":[20,59,72,84,133],"channel":[21,28,64,134,147],"distortion":[22,65],"are":[23,67],"simultaneously":[24],"involved.":[25],"An":[26],"iterative":[27],"estimation":[29],"method":[30],"is":[31,53,119],"integrated":[32],"into":[33],"the":[34,70,89,104,108,114,138,142],"framework":[35],"of":[36,76,103,129],"our":[37],"Parallel":[38],"Combined":[39],"Gaussian":[40],"Mixture":[41],"Model":[42],"(PCGMM)":[43],"based":[44],"algorithm":[47],"[1].":[48],"A":[49],"new":[50],"corpus":[52,92,111,151],"generated":[54,90],"which":[55],"reflects":[56],"both":[57,130],"additive":[58],"convolutional":[60],"corruption.":[62],"The":[63],"effects":[66],"obtained":[68,109],"from":[69],"NTIMIT":[71],"CTIMIT":[73],"corpora.":[74],"Evaluation":[75],"objective":[77],"quality":[79],"measures":[80],"including":[81,141],"STNR,":[82],"PESQ,":[83],"recognition":[86,125],"shows":[87],"that":[88,113],"represents":[93],"highly":[94],"challenging":[95],"acoustic":[96],"conditions":[97],"recognition.":[100,156],"Performance":[101],"evaluation":[102],"proposed":[105,115],"system":[106],"over":[107],"demonstrates":[112],"significantly":[120],"at":[122],"improving":[123],"performance":[126],"with":[127],"presence":[128],"distortion,":[135],"comparing":[136],"conventional":[139],"methods":[140],"ETSI":[143],"AFE.":[144],"Index":[145],"Terms:":[146],"estimation,":[148],"compensation,":[150],"generation,":[152],"PCGMM,":[153]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}