{"id":"https://openalex.org/W2947582273","doi":"https://doi.org/10.1109/spcom.2018.8724480","title":"Some Experiments on Context Mismatched Speech Recognition","display_name":"Some Experiments on Context Mismatched Speech Recognition","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2947582273","doi":"https://doi.org/10.1109/spcom.2018.8724480","mag":"2947582273"},"language":"en","primary_location":{"id":"doi:10.1109/spcom.2018.8724480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2018.8724480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Signal Processing and Communications (SPCOM)","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/A5068608126","display_name":"Abhishek Dey","orcid":"https://orcid.org/0000-0002-7177-6047"},"institutions":[{"id":"https://openalex.org/I138537684","display_name":"Gauhati University","ror":"https://ror.org/01ppj9r51","country_code":"IN","type":"education","lineage":["https://openalex.org/I138537684"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhishek Dey","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Gauhati University, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Gauhati University, India","institution_ids":["https://openalex.org/I138537684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063682063","display_name":"S. Shahnawazuddin","orcid":"https://orcid.org/0000-0002-3916-9693"},"institutions":[{"id":"https://openalex.org/I11793825","display_name":"National Institute of Technology Patna","ror":"https://ror.org/056wyhh33","country_code":"IN","type":"education","lineage":["https://openalex.org/I11793825","https://openalex.org/I4210152752"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Shahnawazuddin","raw_affiliation_strings":["Department of Electronics and Communication Engineering, NIT Patna, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, NIT Patna, India","institution_ids":["https://openalex.org/I11793825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036693781","display_name":"Rohit Sinha","orcid":"https://orcid.org/0000-0002-0419-6501"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohit Sinha","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, IIT Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, IIT Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068608126"],"corresponding_institution_ids":["https://openalex.org/I138537684"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22102609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"247","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9976000189781189,"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":0.8171235918998718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7838338613510132},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6977277994155884},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6009019017219543},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5466173887252808},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4714173972606659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4196946620941162},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.41242432594299316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3326641321182251}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8171235918998718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838338613510132},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6977277994155884},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6009019017219543},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5466173887252808},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4714173972606659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196946620941162},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.41242432594299316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3326641321182251},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom.2018.8724480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2018.8724480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1540779870","https://openalex.org/W2112021726","https://openalex.org/W2121981798","https://openalex.org/W2130722890","https://openalex.org/W2147768505","https://openalex.org/W2152131029","https://openalex.org/W2159300614","https://openalex.org/W2160815625","https://openalex.org/W2164931619","https://openalex.org/W2276408190","https://openalex.org/W2295119550","https://openalex.org/W2403731734","https://openalex.org/W2736786568","https://openalex.org/W6632550522","https://openalex.org/W6679230416","https://openalex.org/W6697090674","https://openalex.org/W6741240231"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W4297807400","https://openalex.org/W1491159402"],"abstract_inverted_index":{"An":[0],"automatic":[1],"speech":[2,52],"recognition":[3,146,182],"(ASR)":[4],"system":[5,86],"is":[6,64,93,115,185,193],"required":[7],"to":[8,27,61,117,123,157],"normalize":[9],"a":[10,55],"number":[11,57,177,190],"of":[12,31,43,50,58,91,95,97,161,174,178,191],"intra-":[13],"and":[14,22,77,103,122],"inter-speaker":[15],"variability":[16,33],"as":[17,19],"well":[18],"session,":[20],"channel":[21],"ambiance":[23],"differences":[24],"in":[25,100,141,195],"order":[26],"be":[28],"effective.":[29],"Some":[30],"the":[32,44,69,85,101,107,119,132,142,145,159,172,176,181],"factors":[34],"are":[35,81,139],"gender,":[36],"age,":[37],"accent,":[38],"emotion,":[39],"speaking":[40],"rate,":[41],"etc.,":[42],"speakers.":[45],"To":[46],"address":[47],"these":[48],"sources":[49],"variability,":[51],"data":[53],"from":[54],"large":[56],"speakers":[59],"catering":[60],"varied":[62],"conditions":[63],"pooled":[65],"together":[66],"for":[67],"training":[68,102],"context-dependent":[70],"triphone":[71,98],"models.":[72],"Furthermore,":[73],"several":[74],"feature-space":[75],"normalization":[76],"speaker-space":[78],"adaptation":[79],"techniques":[80],"also":[82],"incorporated":[83],"into":[84],"development.":[87],"Another":[88],"important":[89],"factor":[90],"mismatch":[92],"frequency":[94],"occurrence":[96],"contexts":[99,121],"test":[104,143],"data.":[105],"In":[106,128,150,167],"case":[108],"hidden":[109],"Markov":[110],"modeling,":[111],"regression-tree-based":[112],"state":[113],"tying":[114],"performed":[116],"model":[118],"seen":[120],"deal":[124],"with":[125],"unseen":[126],"ones.":[127],"those":[129],"cases":[130],"where":[131],"trained":[133],"triphones":[134],"occur":[135],"less":[136],"frequently":[137],"(or":[138],"absent)":[140],"data,":[144],"performance":[147,160],"gets":[148],"degraded.":[149],"this":[151,168],"paper,":[152],"we":[153,170],"present":[154],"our":[155],"efforts":[156],"improve":[158],"such":[162,196],"context":[163],"mismatched":[164],"ASR":[165],"tasks.":[166],"regard,":[169],"explore":[171],"role":[173],"varying":[175],"senones":[179,192],"on":[180],"performance.":[183],"It":[184],"hypothesized":[186],"that,":[187],"using":[188],"lower":[189],"beneficial":[194],"cases.":[197]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}