{"id":"https://openalex.org/W2007645738","doi":"https://doi.org/10.1109/icassp.2013.6639061","title":"Analyzing noise robustness of MFCC and GFCC features in speaker identification","display_name":"Analyzing noise robustness of MFCC and GFCC features in speaker identification","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2007645738","doi":"https://doi.org/10.1109/icassp.2013.6639061","mag":"2007645738"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5102205042","display_name":"Xiaojia Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojia Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101752802","display_name":"Deliang Wang","orcid":"https://orcid.org/0009-0008-6488-0234"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Center for Cognitive Science, Ohio State University, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center for Cognitive Science, Ohio State University, USA","institution_ids":[]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":203,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7204","last_page":"7208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9891999959945679,"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/robustness","display_name":"Robustness (evolution)","score":0.8958898782730103},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8922257423400879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716350317001343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6550453901290894},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6341734528541565},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5143471956253052},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.430826336145401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43040895462036133},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4301643967628479},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4134010672569275}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8958898782730103},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8922257423400879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716350317001343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6550453901290894},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6341734528541565},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5143471956253052},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.430826336145401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43040895462036133},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4301643967628479},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4134010672569275},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.2729","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.2729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Zhao-Wang.icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W123426918","https://openalex.org/W2034329102","https://openalex.org/W2041823554","https://openalex.org/W2061140267","https://openalex.org/W2121061347","https://openalex.org/W2123768812","https://openalex.org/W2150769028","https://openalex.org/W2164432048","https://openalex.org/W2478884216","https://openalex.org/W2561557072","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W4317383455","https://openalex.org/W4234190324","https://openalex.org/W2548511587","https://openalex.org/W2185075503","https://openalex.org/W1996690921","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870"],"abstract_inverted_index":{"Automatic":[0],"speaker":[1,31,65],"recognition":[2],"can":[3],"achieve":[4],"a":[5,29,51,105],"high":[6],"level":[7],"of":[8,54,58],"performance":[9,18],"in":[10,21],"matched":[11],"training":[12],"and":[13,73,98],"testing":[14],"conditions.":[15,24],"However,":[16],"such":[17],"drops":[19],"significantly":[20],"mismatched":[22],"noisy":[23],"Recent":[25],"research":[26],"indicates":[27],"that":[28,78],"new":[30],"feature,":[32],"gammatone":[33],"frequency":[34],"cepstral":[35,46],"coefficients":[36,47],"(GFCC),":[37],"exhibits":[38],"superior":[39],"noise":[40,85],"robustness":[41,57,86,102],"to":[42,61,68,94],"commonly":[43],"used":[44],"mel-frequency":[45],"(MFCC).":[48],"To":[49],"gain":[50],"deep":[52],"understanding":[53],"the":[55,79,84],"intrinsic":[56],"GFCC":[59,101],"relative":[60],"MFCC,":[62],"we":[63],"design":[64],"identification":[66],"experiments":[67],"systematically":[69],"analyze":[70],"their":[71],"differences":[72,87],"similarities.":[74],"This":[75],"study":[76,91],"reveals":[77],"nonlinear":[80],"rectification":[81],"accounts":[82],"for":[83],"primarily.":[88],"Moreover,":[89],"this":[90],"suggests":[92],"how":[93],"enhance":[95],"MFCC":[96],"robustness,":[97],"further":[99],"improve":[100],"by":[103],"adopting":[104],"different":[106],"time-frequency":[107],"representation.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}