{"id":"https://openalex.org/W2765381110","doi":"https://doi.org/10.1109/ncc.2017.8077071","title":"Fusion of spectral and prosodic information using combined error optimization for keyword spotting","display_name":"Fusion of spectral and prosodic information using combined error optimization for keyword spotting","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2765381110","doi":"https://doi.org/10.1109/ncc.2017.8077071","mag":"2765381110"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2017.8077071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","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/A5103065161","display_name":"Laxmi Pandey","orcid":"https://orcid.org/0000-0001-8523-7741"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Laxmi Pandey","raw_affiliation_strings":["Dept. of Electrical Engineering, Indian Institute of Technology, Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Indian Institute of Technology, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107990506","display_name":"Kuldeep Chaudhary","orcid":"https://orcid.org/0000-0003-1295-0313"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kuldeep Chaudhary","raw_affiliation_strings":["Dept. of Electrical Engineering, Indian Institute of Technology, Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Indian Institute of Technology, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085503354","display_name":"Rajesh M. Hegde","orcid":"https://orcid.org/0000-0002-6142-7724"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajesh M Hegde","raw_affiliation_strings":["Dept. of Electrical Engineering, Indian Institute of Technology, Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Indian Institute of Technology, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/keyword-spotting","display_name":"Keyword spotting","score":0.8714005947113037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094168066978455},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.671454131603241},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6599153280258179},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6193788647651672},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6141321063041687},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.570135235786438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5639913082122803},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.5486222505569458},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5319194197654724},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5198450684547424},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43471720814704895},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41946983337402344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16107770800590515}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8714005947113037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094168066978455},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.671454131603241},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6599153280258179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6193788647651672},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6141321063041687},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.570135235786438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5639913082122803},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5486222505569458},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5319194197654724},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5198450684547424},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43471720814704895},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41946983337402344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16107770800590515},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc.2017.8077071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W158901718","https://openalex.org/W1499360075","https://openalex.org/W1538323930","https://openalex.org/W1579838312","https://openalex.org/W1983906381","https://openalex.org/W2002342963","https://openalex.org/W2041823554","https://openalex.org/W2046932483","https://openalex.org/W2101328377","https://openalex.org/W2105594594","https://openalex.org/W2125838338","https://openalex.org/W2143827132","https://openalex.org/W2151402979","https://openalex.org/W2155443942","https://openalex.org/W3147254695","https://openalex.org/W6606482904"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2388033618","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022","https://openalex.org/W2000885660"],"abstract_inverted_index":{"Incorporating":[0],"prosodic":[1,24,60,78],"information":[2,5,25],"with":[3,176],"spectral":[4,22,58,76],"at":[6],"the":[7,35,40,86,91,111,114,126,129,136,142,191,210,213,233,241],"feature":[8,18,70,149,164,238],"level":[9,19],"is":[10,26,31,72,151,166],"challenging.":[11],"In":[12,85],"this":[13,197],"paper,":[14],"a":[15,169,177,229,236],"method":[16],"for":[17,182,196],"fusion":[20,215],"of":[21,39,82,89,113,128,135,155,158,212,222,235],"and":[23,53,59,77,93,203,224],"proposed.":[27],"A":[28],"pitch":[29,52,55,95,116,131],"contour":[30],"first":[32],"extracted":[33,63],"from":[34,64,80],"frame":[36],"blocked":[37],"segments":[38,45,117],"speech":[41,44],"signal.":[42],"These":[43],"obtained":[46,73,120,140,152,219],"herein":[47],"are":[48,62,98,139,188,206],"labeled":[49,96],"as":[50],"high":[51,92,115],"low":[54,94,130],"segments.":[56,132],"Both":[57],"features":[61,79,97,159],"each":[65,81],"segment":[66],"class.":[67],"An":[68],"integrated":[69,148,163],"set":[71,150,165,239],"by":[74,121],"concatenating":[75],"these":[83],"classes.":[84],"next":[87],"stage":[88],"fusion,":[90],"further":[99],"combined":[100],"using":[101,141],"joint":[102],"error":[103],"optimization":[104,107],"approach.":[105,145],"This":[106,162],"approach":[108],"assumes":[109],"that":[110],"mean":[112,127],"can":[118],"be":[119],"an":[122],"affine":[123,137],"transformation":[124,138],"on":[125,190,200],"The":[133,146],"parameters":[134],"gradient":[143],"descent":[144],"final":[147],"after":[153],"normalization":[154],"both":[156],"sets":[157],"thus":[160],"obtained.":[161],"used":[167],"in":[168,220],"Hidden":[170],"Markov":[171],"Modeling":[172],"(HMM)":[173],"framework":[174],"along":[175],"novel":[178],"sliding":[179],"syllable":[180],"protocol":[181],"keyword":[183,201,204],"spotting.":[184],"Keyword":[185],"spotting":[186,205],"experiments":[187],"conducted":[189,207],"Hindi":[192],"language":[193],"database":[194],"developed":[195],"purpose.":[198],"Experiments":[199],"recognition":[202],"to":[208],"evaluate":[209],"performance":[211],"proposed":[214],"method.":[216],"Experimental":[217],"results":[218],"terms":[221],"WER":[223],"receiver":[225],"operating":[226],"characteristics":[227],"indicate":[228],"reasonable":[230],"improvements":[231],"over":[232],"use":[234],"single":[237],"like":[240],"MFCC.":[242]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}