{"id":"https://openalex.org/W2078378161","doi":"https://doi.org/10.1109/icassp.2002.5743768","title":"A simple approach to non-uniform vowel normalization","display_name":"A simple approach to non-uniform vowel normalization","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2078378161","doi":"https://doi.org/10.1109/icassp.2002.5743768","mag":"2078378161"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743768","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"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":true,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110188613","display_name":"S. V. Bharath Kumar","orcid":null},"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":"S. V. Bharath Kumar","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079380091","display_name":"Miranda L. Vinay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. K. Vinay","raw_affiliation_strings":["eMuzed India Pvt Ltd, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"eMuzed India Pvt Ltd, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111873557","display_name":"Rajesh Sharma","orcid":null},"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 Sharma","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA","institution_ids":["https://openalex.org/I94234084"]}]},{"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/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":"Rohit Sinha","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Kanpur, INDIA","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085660348"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":1.4203,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81940874,"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":"I","last_page":"517"},"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":0.9991000294685364,"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":0.9970999956130981,"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/normalization","display_name":"Normalization (sociology)","score":0.9286901950836182},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.8745684623718262},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7946147918701172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6643319129943848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6582297682762146},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5351131558418274},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.44603610038757324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3844304382801056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23725977540016174}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9286901950836182},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.8745684623718262},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7946147918701172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643319129943848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6582297682762146},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5351131558418274},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.44603610038757324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3844304382801056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23725977540016174},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743768","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.8157","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.8157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mkvinay.tripod.com/papers/ICASSP2002IITK.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1963363117","https://openalex.org/W2056133372","https://openalex.org/W2070696251","https://openalex.org/W2133710250","https://openalex.org/W2160437209","https://openalex.org/W2317919972","https://openalex.org/W2498927921","https://openalex.org/W3141061717","https://openalex.org/W6679531511"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2735770592","https://openalex.org/W1971024059","https://openalex.org/W2347413598","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698"],"abstract_inverted_index":{"In":[0],"this":[1,108],"paper,":[2],"we":[3,44],"present":[4,80],"results":[5,81,106],"of":[6,52,82,87],"non-uniform":[7,32,70,92],"vowel":[8,19,33,55,122],"normalization":[9,34,72],"and":[10,36,56,118],"show":[11,37],"that":[12,38,97],"the":[13,24,53,57,100,105],"frequency-warping":[14],"necessary":[15],"to":[16,23,30,68],"do":[17],"nonuniform":[18],"nonnalization":[20],"is":[21,63,99],"similar":[22,47],"mel-scale.":[25],"We":[26,78],"compare":[27],"our":[28,88],"methods":[29],"Fant's":[31],"method":[35],"with":[39],"proposed":[40,61],"frequency":[41],"warping":[42,102],"approach":[43,62],"can":[45],"achieve":[46],"performance":[48],"without":[49],"any":[50],"knowledge":[51],"spoken":[54],"fonnant":[58],"number.":[59],"The":[60],"motivated":[64],"by":[65],"a":[66,83],"desire":[67],"perform":[69],"speaker":[71],"in":[73,107],"automatic":[74],"speech":[75],"recognition":[76],"systems.":[77],"also":[79],"more":[84],"comprehensive":[85],"study":[86],"earlier":[89],"work":[90],"on":[91,112],"scaling":[93],"which":[94],"again":[95],"shows":[96],"mel-scale":[98],"appropriate":[101],"function.":[103],"All":[104],"paper":[109],"are":[110],"based":[111],"data":[113],"from":[114],"Peterson":[115],"&":[116],"Barney":[117],"Hillenbrand":[119],"et":[120],"al.":[121],"databases.":[123]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}