{"id":"https://openalex.org/W2114156775","doi":"https://doi.org/10.21437/interspeech.2010-217","title":"Revisiting VTLN using linear transformation on conventional MFCC","display_name":"Revisiting VTLN using linear transformation on conventional MFCC","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2114156775","doi":"https://doi.org/10.21437/interspeech.2010-217","mag":"2114156775"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-217","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-196163%22","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Doddipatla Rama Sanand","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Doddipatla Rama Sanand","raw_affiliation_strings":["[Rwth Aachen University]"],"affiliations":[{"raw_affiliation_string":"[Rwth Aachen University]","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":2.3318,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8993706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"541"},"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":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7362242937088013},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6595158576965332},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6289505958557129},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6119358539581299},{"id":"https://openalex.org/keywords/linear-map","display_name":"Linear map","score":0.6043758988380432},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5663120150566101},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4978170394897461},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4811016917228699},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4460761547088623},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39634719491004944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3862883448600769},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3297419548034668},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22715964913368225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10246220231056213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362242937088013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6595158576965332},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6289505958557129},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6119358539581299},{"id":"https://openalex.org/C49766605","wikidata":"https://www.wikidata.org/wiki/Q207643","display_name":"Linear map","level":2,"score":0.6043758988380432},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5663120150566101},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4978170394897461},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4811016917228699},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4460761547088623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39634719491004944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3862883448600769},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3297419548034668},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22715964913368225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10246220231056213},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-217","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:125715","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/125715","pdf_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-196163%22","source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"NEUEZEILEProceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech 2010) : 26 - 30 September, 2010, Makuhari, Chiba, Japan<br/>11. Annual Conference of the International Speech Communication Association, Interspeech 2010, Chiba, Japan, 2010-09-26 - 2010-09-30","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:publications.rwth-aachen.de:125715","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/125715","pdf_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-196163%22","source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"NEUEZEILEProceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech 2010) : 26 - 30 September, 2010, Makuhari, Chiba, Japan<br/>11. Annual Conference of the International Speech Communication Association, Interspeech 2010, Chiba, Japan, 2010-09-26 - 2010-09-30","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2114156775.pdf","grobid_xml":"https://content.openalex.org/works/W2114156775.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2964579","https://openalex.org/W38163879","https://openalex.org/W193437634","https://openalex.org/W2139246688","https://openalex.org/W2164931619","https://openalex.org/W2169878657"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2591697403","https://openalex.org/W4252379076","https://openalex.org/W4385195690","https://openalex.org/W2766569399","https://openalex.org/W2156831951","https://openalex.org/W1992816027","https://openalex.org/W1510175409","https://openalex.org/W1996753822"],"abstract_inverted_index":{"In":[0],"this":[1,48],"paper,":[2,49],"we":[3,50],"revisit":[4,82],"the":[5,21,38,53,60,73,83,95,100,108,112,119],"linear":[6,84,113,131],"transformation":[7,85,114,132],"for":[8,44,86],"VTLN":[9,87,121,128],"on":[10,63,76,133],"conventional":[11,120,134],"MFCC":[12],"proposed":[13,109],"by":[14],"Sanand":[15],"et":[16],"al.":[17],"in":[18,68,88],"[1],":[19],"using":[20,129],"idea":[22],"of":[23,97],"band-limited":[24],"interpolation.The":[25],"filter-bank":[26,54],"is":[27,42],"modified":[28],"to":[29,81,93,111,126],"include":[30],"half-filters":[31,56,98],"at":[32],"zero":[33],"and":[34,90],"nyquist":[35],"frequencies,":[36],"as":[37,118],"full":[39],"symmetric":[40],"spectrum":[41],"required":[43],"performing":[45],"bandlimited":[46],"interpolation.In":[47],"show":[51,103],"that":[52,107],"with":[55],"does":[57,71],"not":[58],"affect":[59,72,96],"recognition":[61,74,105],"performance":[62,75,117],"clean":[64],"speech":[65],"(also":[66],"shown":[67],"[1]),":[69],"but":[70],"noisy":[77],"speech.This":[78],"motivated":[79],"us":[80,125],"[1]":[89],"propose":[91],"modifications":[92,110],"undo":[94],"during":[99],"feature":[101],"extraction.We":[102],"through":[104],"experiments":[106],"have":[115],"comparable":[116],"approach,":[122],"still":[123],"enabling":[124],"perform":[127],"a":[130],"MFCC.":[135]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}