{"id":"https://openalex.org/W2947885768","doi":"https://doi.org/10.1109/spcom.2018.8724428","title":"Detection of Vowel Offset Points Using Non-Local Similarity Between Speech Samples","display_name":"Detection of Vowel Offset Points Using Non-Local Similarity Between Speech Samples","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2947885768","doi":"https://doi.org/10.1109/spcom.2018.8724428","mag":"2947885768"},"language":"en","primary_location":{"id":"doi:10.1109/spcom.2018.8724428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2018.8724428","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/A5059592615","display_name":"Avinash Kumar","orcid":"https://orcid.org/0000-0001-7953-0247"},"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":true,"raw_author_name":"Avinash Kumar","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":"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/A5038771729","display_name":"Gayadhar Pradhan","orcid":"https://orcid.org/0000-0001-7385-6684"},"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":"Gayadhar Pradhan","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059592615"],"corresponding_institution_ids":["https://openalex.org/I11793825"],"apc_list":null,"apc_paid":null,"fwci":0.332,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60591037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"256"},"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":0.9990000128746033,"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/vowel","display_name":"Vowel","score":0.8333427906036377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6648937463760376},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5565142035484314},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5466029644012451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5228046178817749},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5056102275848389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4811743199825287},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.478958398103714},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4443337619304657},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.43815144896507263},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4367712736129761},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11447453498840332}],"concepts":[{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.8333427906036377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6648937463760376},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5565142035484314},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5466029644012451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5228046178817749},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5056102275848389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4811743199825287},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.478958398103714},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4443337619304657},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.43815144896507263},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4367712736129761},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11447453498840332},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom.2018.8724428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2018.8724428","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W129004689","https://openalex.org/W1849183145","https://openalex.org/W1964897957","https://openalex.org/W1974387177","https://openalex.org/W1980931161","https://openalex.org/W1981706894","https://openalex.org/W1986501036","https://openalex.org/W2001105330","https://openalex.org/W2001802849","https://openalex.org/W2006434523","https://openalex.org/W2008884494","https://openalex.org/W2030879331","https://openalex.org/W2034766634","https://openalex.org/W2048175496","https://openalex.org/W2059980860","https://openalex.org/W2097073572","https://openalex.org/W2097176846","https://openalex.org/W2121981798","https://openalex.org/W2143131425","https://openalex.org/W2144033509","https://openalex.org/W2147768505","https://openalex.org/W2153954176","https://openalex.org/W2168201882","https://openalex.org/W2253740514","https://openalex.org/W2330773306","https://openalex.org/W2514707631","https://openalex.org/W2518161968","https://openalex.org/W2739418057","https://openalex.org/W2746756894","https://openalex.org/W2750393895","https://openalex.org/W4245838404","https://openalex.org/W6650658821","https://openalex.org/W6726024243","https://openalex.org/W6741819138"],"related_works":["https://openalex.org/W2028715205","https://openalex.org/W2344358524","https://openalex.org/W3042758298","https://openalex.org/W2060888333","https://openalex.org/W2053092242","https://openalex.org/W2028342517","https://openalex.org/W2050311283","https://openalex.org/W2942435052","https://openalex.org/W3169184738","https://openalex.org/W2007544974"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,71],"of":[2,21,23,38,42,64,72,80,90,122,186,259],"vowels":[3,39,171],"is":[4,18,54,103,153,217,234],"not":[5],"only":[6],"an":[7],"important":[8,34],"but":[9],"also":[10,84],"a":[11,24,97,140,220,227,260],"challenging":[12],"problem.":[13],"Vowel":[14],"offset":[15],"point":[16],"(VEP)":[17],"the":[19,48,52,60,65,70,77,81,88,107,110,113,123,128,132,149,157,166,170,184,190,194,197,201,215,224,238,257],"instant":[20],"ending":[22],"vowel.":[25],"Like":[26],"vowel":[27],"onset":[28],"points":[29,125],"(VOPs),":[30],"VEPs":[31,53,225],"are":[32,118,161,172],"equally":[33],"for":[35,69,105,222],"accurate":[36],"marking":[37],"and":[40,175,204,251],"analysis":[41],"speech":[43,92,100,229,263],"signal.":[44,230],"The":[45,143,231],"transition":[46],"in":[47,87,131,163,183,226],"signal":[49],"magnitude":[50],"at":[51,109],"quite":[55],"different":[56,137],"when":[57,156],"compared":[58],"to":[59,75,120,135,165,189,200,236],"VOPs.":[61],"Consequently,":[62],"most":[63],"front-end":[66],"features":[67,83],"proposed":[68,104,114,232,262],"VOPs":[73],"fail":[74],"detect":[76],"VEPs.":[78,111],"Performance":[79],"existing":[82],"reduces":[85],"significantly":[86,154],"case":[89,185],"noisy":[91,252],"signals.":[93],"In":[94,112,209],"this":[95,210],"work,":[96,211],"robust":[98],"frontend":[99],"parametrization":[101],"approach":[102],"enhancing":[106],"discrimination":[108],"approach,":[115],"weight":[116,144],"values":[117,145],"assigned":[119],"each":[121],"sample":[124],"by":[126],"computing":[127],"similarity":[129,151,182],"present":[130],"samples":[133],"belonging":[134,188,199],"two":[136],"frames":[138,158,187,198],"within":[139],"search":[141],"neighborhood.":[142],"(WVs)":[146],"computed":[147,213],"from":[148,214],"non-local":[150],"(NLS)":[152],"less":[155],"under":[159,248],"consideration":[160],"similar":[162],"comparison":[164],"dissimilar":[167],"ones.":[168],"Since":[169],"longer":[173],"regions":[174,203],"exhibit":[176],"periodicity,":[177],"there":[178],"will":[179,206],"be":[180,207],"more":[181],"these":[191],"regions.":[192],"On":[193],"other":[195],"hand,":[196],"non-vowel":[202],"noises":[205],"dissimilar.":[208],"WVs":[212],"NLS":[216],"used":[218],"as":[219],"feature":[221],"detecting":[223],"given":[228],"method":[233],"observed":[235],"outperform":[237],"deep":[239],"neural":[240],"network":[241],"-":[242],"hidden":[243],"Markov":[244],"model":[245],"based":[246],"classifier":[247],"both":[249],"clean":[250],"test":[253],"conditions":[254],"even":[255],"after":[256],"inclusion":[258],"recently":[261],"enhancement":[264],"module.":[265]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}