{"id":"https://openalex.org/W2106405099","doi":"https://doi.org/10.1109/icassp.2012.6288855","title":"Spectro-temporal Gabor features for speaker recognition","display_name":"Spectro-temporal Gabor features for speaker recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2106405099","doi":"https://doi.org/10.1109/icassp.2012.6288855","mag":"2106405099"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5036206336","display_name":"Howard Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Howard Lei","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061251853","display_name":"Nikki Mirghafori","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikki Mirghafori","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036206336"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":4.8619,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95054866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"4241","last_page":"4244"},"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":0.998199999332428,"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":0.9955999851226807,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7925636768341064},{"id":"https://openalex.org/keywords/gabor-transform","display_name":"Gabor transform","score":0.6973386406898499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6714286804199219},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6641483306884766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.66220623254776},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6272602677345276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6036179065704346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5579949021339417},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.549192488193512},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4466342628002167},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.3700239658355713},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.23149746656417847}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7925636768341064},{"id":"https://openalex.org/C173149727","wikidata":"https://www.wikidata.org/wiki/Q996397","display_name":"Gabor transform","level":4,"score":0.6973386406898499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6714286804199219},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6641483306884766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.66220623254776},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6272602677345276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6036179065704346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5579949021339417},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.549192488193512},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4466342628002167},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.3700239658355713},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.23149746656417847},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.9201","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.9201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/gaborfeatures12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W9692546","https://openalex.org/W34609997","https://openalex.org/W111477576","https://openalex.org/W1576520375","https://openalex.org/W1583620810","https://openalex.org/W1990934990","https://openalex.org/W2041823554","https://openalex.org/W2097470427","https://openalex.org/W2103438437","https://openalex.org/W2147147599","https://openalex.org/W2158010000","https://openalex.org/W2166067691","https://openalex.org/W2400523955","https://openalex.org/W2416509206","https://openalex.org/W6600365384","https://openalex.org/W6601395909","https://openalex.org/W6604441197","https://openalex.org/W6634442568","https://openalex.org/W6716634338"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W3119288895","https://openalex.org/W2390244057","https://openalex.org/W2606578966","https://openalex.org/W2185075503","https://openalex.org/W2360182727","https://openalex.org/W2749720872","https://openalex.org/W1905998934","https://openalex.org/W2384007269","https://openalex.org/W2186375278"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"have":[4,21,32],"investigated":[5],"the":[6,55,59,66,92,104],"performance":[7],"of":[8,73,94,106],"2D":[9],"Gabor":[10,19,38,60,74,107],"features":[11,20,61,68,77,87,108],"(known":[12],"as":[13,63,65],"spectro-temporal":[14],"features)":[15],"for":[16,25,100],"speaker":[17,44],"recognition.":[18],"been":[22],"used":[23],"mainly":[24],"automatic":[26],"speech":[27],"recognition":[28,45],"(ASR),":[29],"where":[30],"they":[31],"yielded":[33],"improvements.":[34],"We":[35],"explored":[36],"different":[37,43],"feature":[39,101],"implementations,":[40],"along":[41],"with":[42],"approaches,":[46],"on":[47],"ROSSI":[48,57],"[1]":[49],"and":[50,70,75,97,103],"NIST":[51],"SRE08":[52],"databases.":[53],"Using":[54],"noisy":[56],"database,":[58],"performed":[62],"well":[64],"MFCC":[67,76,86,110],"standalone,":[69],"score-level":[71],"combination":[72],"resulted":[78],"in":[79],"an":[80],"8%":[81],"relative":[82],"EER":[83],"improvement":[84],"over":[85],"standalone.":[88],"These":[89],"results":[90],"demonstrated":[91],"value":[93],"both":[95],"spectral":[96],"temporal":[98],"information":[99],"extraction,":[102],"complementarity":[105],"to":[109],"features.":[111]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}