{"id":"https://openalex.org/W2129886857","doi":"https://doi.org/10.1109/icarcv.2004.1468885","title":"A bilinear transform approach for vocal tract length normalization","display_name":"A bilinear transform approach for vocal tract length normalization","publication_year":2005,"publication_date":"2005-07-27","ids":{"openalex":"https://openalex.org/W2129886857","doi":"https://doi.org/10.1109/icarcv.2004.1468885","mag":"2129886857"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv.2004.1468885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2004.1468885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004.","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/A5000048946","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0002-7585-759X"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]},{"id":"https://openalex.org/I4210094772","display_name":"Henan University of Engineering","ror":"https://ror.org/007wym039","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210094772"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Wang","raw_affiliation_strings":["Information and Engineering University, Zhengzhou, Henan, China","Inf. Eng. Univ., Henan, China"],"affiliations":[{"raw_affiliation_string":"Information and Engineering University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"Inf. Eng. Univ., Henan, China","institution_ids":["https://openalex.org/I4210094772"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang Bing-xi","orcid":null},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]},{"id":"https://openalex.org/I4210094772","display_name":"Henan University of Engineering","ror":"https://ror.org/007wym039","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210094772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Bing-xi","raw_affiliation_strings":["Information and Engineering University, Zhengzhou, Henan, China","Inf. Eng. Univ., Henan, China"],"affiliations":[{"raw_affiliation_string":"Information and Engineering University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"Inf. Eng. Univ., Henan, China","institution_ids":["https://openalex.org/I4210094772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101299930","display_name":"Qi Ding","orcid":"https://orcid.org/0009-0009-5696-8583"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]},{"id":"https://openalex.org/I4210094772","display_name":"Henan University of Engineering","ror":"https://ror.org/007wym039","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210094772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Qi","raw_affiliation_strings":["Information and Engineering University, Zhengzhou, Henan, China","Inf. Eng. Univ., Henan, China"],"affiliations":[{"raw_affiliation_string":"Information and Engineering University, Zhengzhou, Henan, China","institution_ids":["https://openalex.org/I169689159"]},{"raw_affiliation_string":"Inf. Eng. Univ., Henan, China","institution_ids":["https://openalex.org/I4210094772"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000048946"],"corresponding_institution_ids":["https://openalex.org/I169689159","https://openalex.org/I4210094772"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14645209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"547","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9961000084877014,"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/vocal-tract","display_name":"Vocal tract","score":0.9315281510353088},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8866689801216125},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7743961811065674},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.6784374117851257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6419249176979065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6405172348022461},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5730261206626892},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5113994479179382},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47743114829063416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4167579412460327},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.23126447200775146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1840357482433319}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.9315281510353088},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8866689801216125},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7743961811065674},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.6784374117851257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419249176979065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6405172348022461},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5730261206626892},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5113994479179382},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47743114829063416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4167579412460327},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23126447200775146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1840357482433319},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/icarcv.2004.1468885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2004.1468885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W119936418","https://openalex.org/W1766888123","https://openalex.org/W2102378903","https://openalex.org/W2139488802","https://openalex.org/W2140567543","https://openalex.org/W2164317961","https://openalex.org/W2164931619","https://openalex.org/W6604811663"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2045900265","https://openalex.org/W2131046383"],"abstract_inverted_index":{"We":[0],"have":[1],"developed":[2],"and":[3,39,92,115],"evaluated":[4],"a":[5],"set":[6,72],"of":[7,24,27,49,64,70,73,89,103,113],"speaker":[8,74,98],"normalization":[9,75,99],"procedures":[10,76],"derived":[11],"by":[12,55],"bilinear":[13],"transform":[14],"(BLT)":[15],"to":[16,60,95,108],"compensate":[17],"for":[18],"variations":[19],"in":[20,79],"vocal":[21],"tract":[22],"lengths":[23],"different":[25],"classes":[26],"speakers.":[28],"The":[29,47,68,101],"warping":[30],"factors":[31],"are":[32,53],"estimated":[33],"using":[34,84],"the":[35,44,50,56,62,65,118],"average":[36],"third":[37],"formants":[38],"their":[40,106],"bandwidth,":[41],"leaving":[42],"out":[43],"exhaustive":[45],"search.":[46],"MFCC":[48],"testing":[51],"data":[52],"transformed":[54],"warped":[57],"Mel":[58],"filterbanks":[59],"match":[61],"models":[63],"training":[66],"data.":[67],"effectiveness":[69],"this":[71],"is":[77],"examined":[78],"an":[80,85],"experimental":[81],"study":[82],"performed":[83],"isolated":[86],"digit":[87],"database":[88],"man,":[90],"woman":[91],"children":[93],"comparing":[94],"other":[96],"standard":[97],"method.":[100],"results":[102],"experiments":[104],"demonstrate":[105],"capacity":[107],"achieve":[109],"recognition":[110],"accuracy":[111],"increase":[112],"19.5%":[114],"16.5%":[116],"at":[117],"best.":[119]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}