{"id":"https://openalex.org/W239898915","doi":"https://doi.org/10.21437/interspeech.2012-485","title":"Phoneme class based adaptation for mismatch acoustic modeling of distant noisy speech","display_name":"Phoneme class based adaptation for mismatch acoustic modeling of distant noisy speech","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W239898915","doi":"https://doi.org/10.21437/interspeech.2012-485","mag":"239898915"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-485","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"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/A5046129538","display_name":"Se\u00e7kin Uluskan","orcid":"https://orcid.org/0000-0002-1527-9302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Se\u00e7kin Uluskan","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03319952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1780","last_page":"1783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9979000091552734,"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/timit","display_name":"TIMIT","score":0.7824515104293823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7346286773681641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7254108190536499},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6998286843299866},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.668658435344696},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5847707390785217},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.51186603307724},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49206680059432983},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4512660503387451},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44403451681137085},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.43619537353515625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4022753834724426},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34537214040756226},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3437856435775757},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09862497448921204},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0665925145149231}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7824515104293823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7346286773681641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254108190536499},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6998286843299866},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.668658435344696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5847707390785217},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.51186603307724},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49206680059432983},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4512660503387451},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44403451681137085},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.43619537353515625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4022753834724426},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34537214040756226},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3437856435775757},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09862497448921204},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0665925145149231},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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":1,"locations":[{"id":"doi:10.21437/interspeech.2012-485","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W26405188","https://openalex.org/W262970172","https://openalex.org/W1668904664","https://openalex.org/W2095941401","https://openalex.org/W2157351038","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2121652828","https://openalex.org/W2015876361","https://openalex.org/W4288040805"],"abstract_inverted_index":{"Abstract":[0],":":[1],"A":[2],"new":[3,118,143],"adaptation":[4,29,40,104,134],"strategy":[5,68],"for":[6,17,106,135],"distant":[7,44,76,149],"noisy":[8,77],"speech":[9,78],"is":[10,63],"created":[11,131],"by":[12,126,132],"phoneme":[13,108],"class":[14,109],"based":[15,39],"approaches":[16,25],"context":[18],"independent":[19],"acoustic":[20,32,49,86,121],"models.":[21],"Unlike":[22],"the":[23,35,43,71,112],"previous":[24],"such":[26],"as":[27],"MLLR-MAP":[28,133],"which":[30,51,69,123],"adapts":[31,42],"model":[33,50,87],"to":[34,47,64,81,110],"features,":[36],"our":[37,48],"phoneme-class":[38],"(PCBA)":[41],"data":[45],"features":[46,116],"has":[52],"trained":[53],"on":[54],"close":[55,84],"microphone":[56,85],"TIMIT":[57],"sentences.":[58],"The":[59],"essence":[60],"of":[61,73,75,83,148],"PCBA":[62,127,140],"create":[65],"a":[66,99,142],"transformation":[67],"makes":[70],"distribution":[72],"phoneme-classes":[74],"be":[79],"similar":[80],"those":[82,130],"in":[88,94,146],"thirteen":[89],"dimensional":[90],"MFCC":[91],"space":[92],"(mostly":[93],"c0-c1":[95],"plane).":[96],"It":[97],"creates":[98],"mean,":[100],"orientation":[101],"and":[102,117,119,137],"variance":[103],"scheme":[105],"each":[107],"compensate":[111],"mismatch.":[113],"New":[114],"adapted":[115],"improved":[120],"models":[122],"are":[124,128],"produced":[125],"outperforming":[129],"ASR":[136],"KWS.":[138],"And":[139],"offers":[141],"powerful":[144],"understanding":[145],"acoustic-modeling":[147],"speech.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
