{"id":"https://openalex.org/W2138324695","doi":"https://doi.org/10.1109/icassp.2004.1325926","title":"Using Haar transformed vocal source information for automatic speaker recognition","display_name":"Using Haar transformed vocal source information for automatic speaker recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2138324695","doi":"https://doi.org/10.1109/icassp.2004.1325926","mag":"2138324695"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5078485183","display_name":"Nengheng Zheng","orcid":"https://orcid.org/0000-0002-4493-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nengheng Zheng","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","Dept of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062365583","display_name":"P.C. Ching","orcid":"https://orcid.org/0000-0002-4692-8707"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"P.C. Ching","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","Dept of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.8821,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.7369552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"77"},"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":0.9994999766349792,"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":0.9970999956130981,"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/speech-recognition","display_name":"Speech recognition","score":0.7529929876327515},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7450737357139587},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6919254064559937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6567161083221436},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.6032648682594299},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5702506899833679},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5630311965942383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5254127979278564},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5198112726211548},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4871203899383545},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4331490993499756},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4225016236305237},{"id":"https://openalex.org/keywords/haar","display_name":"Haar","score":0.41783997416496277}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7529929876327515},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7450737357139587},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6919254064559937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6567161083221436},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.6032648682594299},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5702506899833679},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5630311965942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254127979278564},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5198112726211548},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4871203899383545},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4331490993499756},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4225016236305237},{"id":"https://openalex.org/C187029792","wikidata":"https://www.wikidata.org/wiki/Q2179112","display_name":"Haar","level":3,"score":0.41783997416496277},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp.2004.1325926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1563235770","https://openalex.org/W1945468527","https://openalex.org/W1966264494","https://openalex.org/W1988571961","https://openalex.org/W1997873121","https://openalex.org/W2022399586","https://openalex.org/W2069883713","https://openalex.org/W2074263569","https://openalex.org/W2118209063","https://openalex.org/W2603019565"],"related_works":["https://openalex.org/W1482212662","https://openalex.org/W2100012411","https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W1997579527","https://openalex.org/W3044927199","https://openalex.org/W2102353451","https://openalex.org/W2018086531","https://openalex.org/W2387604097","https://openalex.org/W2394579548"],"abstract_inverted_index":{"This":[0,78],"paper":[1],"attempts":[2],"to":[3,23,38,51,74,94],"investigate":[4],"the":[5,28,39,52,75,83,87,95,107,111,137],"effectiveness":[6],"of":[7,42,64,86,120,140],"incorporating":[8],"vocal":[9,127,132],"source":[10,88,133],"information":[11,134],"for":[12],"enhancing":[13],"automatic":[14],"speaker":[15,113],"recognition":[16,123],"accuracy.":[17],"We":[18],"propose":[19],"a":[20,71],"new":[21],"method":[22],"extract":[24],"discriminative":[25,114],"features":[26],"from":[27],"linear":[29,55],"prediction":[30],"(LP)":[31],"residual":[32],"signal,":[33],"which":[34],"are":[35,92],"closely":[36],"related":[37,93],"glottal":[40],"excitation":[41,89],"individual":[43],"speaker.":[44],"A":[45],"complementary":[46],"parameter":[47],"set":[48],"in":[49],"addition":[50],"commonly":[53],"used":[54],"predictive":[56],"cepstral":[57],"coefficients":[58,63],"(LPCC),":[59],"called":[60],"Haar":[61,72],"octave":[62],"residue":[65],"(HOCOR),":[66],"is":[67],"obtained":[68],"by":[69],"applying":[70],"transform":[73],"LP":[76],"residue.":[77],"additional":[79],"feature":[80,129],"vector":[81],"retains":[82],"spectro-temporal":[84],"characteristics":[85],"sequences":[90],"that":[91],"fundamental":[96],"frequency,":[97],"harmonics,":[98],"as":[99,101],"well":[100],"their":[102],"phases.":[103],"Experimental":[104],"evaluation":[105],"over":[106],"YOHO":[108],"corpus":[109],"demonstrates":[110],"high":[112,117],"power":[115],"and":[116,131],"inter-speaker":[118],"variability":[119],"HOCOR.":[121],"Speaker":[122],"tests":[124],"with":[125],"both":[126],"tract":[128],"(LPCC)":[130],"(HOCOR)":[135],"outperform":[136],"conventional":[138],"methods":[139],"using":[141],"LPCC":[142],"only.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}