{"id":"https://openalex.org/W2143926343","doi":"https://doi.org/10.1109/isspit.2010.5711789","title":"Effect of MFCC normalization on vector quantization based speaker identification","display_name":"Effect of MFCC normalization on vector quantization based speaker identification","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2143926343","doi":"https://doi.org/10.1109/isspit.2010.5711789","mag":"2143926343"},"language":"en","primary_location":{"id":"doi:10.1109/isspit.2010.5711789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit.2010.5711789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 10th IEEE International Symposium on Signal Processing and Information Technology","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/A5008842049","display_name":"Sajad Shirali-Shahreza","orcid":"https://orcid.org/0000-0001-5946-3243"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"M. Hassan Shirali-Shahreza","raw_affiliation_strings":["Virtual Education Graduate College, Amirkabir University of Technology\uc2a0, Iran","Virtual Education Graduate College, Amirkabir University of Technology, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virtual Education Graduate College, Amirkabir University of Technology\uc2a0, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"Virtual Education Graduate College, Amirkabir University of Technology, Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032414956","display_name":"Sajad Shirali-Shahreza","orcid":"https://orcid.org/0000-0003-1654-6385"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sajad Shirali-Shahreza","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada","Department of Computer Science University of Toronto, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science University of Toronto, Canada#TAB#","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5449,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.65912724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.996399998664856,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9355714321136475},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8684900999069214},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.8074984550476074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7354466319084167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6720215082168579},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6183270215988159},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5776868462562561},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5435497760772705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5364136695861816},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5350701808929443},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.47587648034095764},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4595782458782196},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11909431219100952}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9355714321136475},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8684900999069214},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.8074984550476074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7354466319084167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720215082168579},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6183270215988159},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5776868462562561},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5435497760772705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364136695861816},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5350701808929443},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.47587648034095764},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4595782458782196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11909431219100952},{"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":1,"locations":[{"id":"doi:10.1109/isspit.2010.5711789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit.2010.5711789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 10th IEEE International Symposium on Signal Processing and Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W192922316","https://openalex.org/W1560013842","https://openalex.org/W1945356021","https://openalex.org/W2005368293","https://openalex.org/W2008957275","https://openalex.org/W2069883713","https://openalex.org/W2099124598","https://openalex.org/W2105710497","https://openalex.org/W2121061347","https://openalex.org/W2121178298","https://openalex.org/W2134383396","https://openalex.org/W2619993508","https://openalex.org/W6607914069"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2432604435","https://openalex.org/W2089229568","https://openalex.org/W2019490789","https://openalex.org/W1911208119","https://openalex.org/W2789994503","https://openalex.org/W3088722891","https://openalex.org/W3204851989"],"abstract_inverted_index":{"Mel":[0],"Frequency":[1],"Cepstral":[2],"Coefficients":[3],"(MFCC)":[4],"are":[5,16],"widely":[6],"used":[7,21],"in":[8],"speech":[9],"recognition":[10],"and":[11,31,34],"speaker":[12,66],"identification.":[13],"MFCC":[14,38],"features":[15],"usually":[17],"pre-processed":[18],"before":[19],"being":[20],"for":[22],"recognition.":[23],"One":[24],"of":[25,54,61],"these":[26,55],"pre-processing":[27,44],"is":[28,45,69,73,80],"creating":[29],"delta":[30],"delta-delta":[32],"coefficients":[33,46],"append":[35],"them":[36],"to":[37,39],"create":[40],"feature":[41],"vector.":[42],"Another":[43],"mean":[47],"normalization.":[48],"In":[49],"this":[50],"paper,":[51],"the":[52,59,85],"effect":[53],"two":[56],"processes":[57],"on":[58],"accuracy":[60],"a":[62],"Vector":[63],"Quantization":[64],"(VQ)":[65],"identification":[67],"system":[68],"compared.":[70],"Additionally,":[71],"it":[72],"shown":[74],"that":[75],"coefficient":[76],"variance":[77],"normalization,":[78],"which":[79],"less":[81],"common,":[82],"can":[83],"improve":[84],"accuracy.":[86]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}