{"id":"https://openalex.org/W12041488","doi":"https://doi.org/10.21437/interspeech.2011-131","title":"Harmonic structure transform for speaker recognition","display_name":"Harmonic structure transform for speaker recognition","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W12041488","doi":"https://doi.org/10.21437/interspeech.2011-131","mag":"12041488"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-131","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5030859194","display_name":"Kornel Laskowski","orcid":"https://orcid.org/0009-0008-8060-6913"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kornel Laskowski","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030859194"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00077735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"365","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9975000023841858,"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":0.9119287729263306},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.8217540979385376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6696072816848755},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6576200127601624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6176626682281494},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5078299641609192},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4665168523788452},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.46064454317092896},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44236618280410767},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36757659912109375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3660137355327606},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.28634482622146606},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15629178285598755},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1059417724609375}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9119287729263306},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8217540979385376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6696072816848755},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6576200127601624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176626682281494},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5078299641609192},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4665168523788452},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.46064454317092896},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44236618280410767},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36757659912109375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3660137355327606},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.28634482622146606},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15629178285598755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1059417724609375},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-131","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W62144079","https://openalex.org/W92500784","https://openalex.org/W180973252","https://openalex.org/W805121765","https://openalex.org/W1538905335","https://openalex.org/W2038959083","https://openalex.org/W2121178298","https://openalex.org/W2154278880"],"related_works":["https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2125446021","https://openalex.org/W3150393935","https://openalex.org/W2980055100","https://openalex.org/W2186790562","https://openalex.org/W2548564146","https://openalex.org/W2756038079"],"abstract_inverted_index":{"We":[0],"evaluate":[1],"a":[2,14,45,60],"new":[3],"filterbank":[4,24],"structure,":[5],"yielding":[6],"the":[7,23],"harmonic":[8],"structure":[9],"cepstral":[10,63],"coefficients":[11],"(HSCCs),":[12],"on":[13],"mismatched-session":[15],"closed-set":[16],"speaker":[17],"classification":[18],"task.":[19],"The":[20,54],"novelty":[21],"of":[22,29,72],"lies":[25],"in":[26,48],"its":[27],"averaging":[28],"energy":[30],"at":[31],"frequencies":[32],"related":[33],"by":[34,38],"harmonicity":[35],"rather":[36],"than":[37],"adjacency.":[39],"Improvements":[40],"are":[41,57],"presented":[42],"which":[43,79],"achieve":[44],"37%rel":[46],"reduction":[47],"error":[49,69],"rate":[50,70],"under":[51],"these":[52],"conditions.":[53],"improved":[55],"features":[56],"combined":[58],"with":[59],"similar":[61],"Mel-frequency":[62],"coefficient":[64],"(MFCC)":[65],"system":[66],"to":[67,82,85],"yield":[68],"reductions":[71],"32%rel,":[73],"suggesting":[74],"that":[75,83],"HSCCs":[76],"offer":[77],"information":[78],"is":[80],"complimentary":[81],"available":[84],"today's":[86],"MFCC-based":[87],"systems.":[88]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
