{"id":"https://openalex.org/W2564006212","doi":"https://doi.org/10.1109/eusipco.2016.7760630","title":"Combining the glottal mixture model (GLOMM) with UBM for speaker recognition","display_name":"Combining the glottal mixture model (GLOMM) with UBM for speaker recognition","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2564006212","doi":"https://doi.org/10.1109/eusipco.2016.7760630","mag":"2564006212"},"language":"en","primary_location":{"id":"doi:10.1109/eusipco.2016.7760630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2016.7760630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 24th European Signal Processing Conference (EUSIPCO)","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/A5013350630","display_name":"Paul M. Baggenstoss","orcid":"https://orcid.org/0000-0002-3739-6104"},"institutions":[{"id":"https://openalex.org/I4210166245","display_name":"Fraunhofer Institute for Communication, Information Processing and Ergonomics","ror":"https://ror.org/05nn0gw40","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166245","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Paul M. Baggenstoss","raw_affiliation_strings":["Fraunhofer FKIE, Fraunhoferstrasse 2053343 Wachtberg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer FKIE, Fraunhoferstrasse 2053343 Wachtberg, Germany","institution_ids":["https://openalex.org/I4210166245"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013350630"],"corresponding_institution_ids":["https://openalex.org/I4210166245"],"apc_list":null,"apc_paid":null,"fwci":0.4285,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.800759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2156","last_page":"2160"},"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":0.9990000128746033,"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":0.9983999729156494,"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":0.7950201034545898},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7901259064674377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7173233032226562},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6984919309616089},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5969563722610474},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5738726854324341},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5311480760574341},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5183423757553101},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4371778666973114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39934468269348145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34344473481178284},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.30004972219467163}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7950201034545898},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7901259064674377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173233032226562},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6984919309616089},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5969563722610474},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5738726854324341},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5311480760574341},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5183423757553101},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4371778666973114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39934468269348145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34344473481178284},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30004972219467163},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/eusipco.2016.7760630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2016.7760630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 24th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/396579","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/396579","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W78415016","https://openalex.org/W331122167","https://openalex.org/W1541505381","https://openalex.org/W1869017930","https://openalex.org/W2013122693","https://openalex.org/W2041823554","https://openalex.org/W2094356263","https://openalex.org/W2118209063","https://openalex.org/W2150769028","https://openalex.org/W2198162819","https://openalex.org/W2493208079","https://openalex.org/W4299808557","https://openalex.org/W6611267404","https://openalex.org/W6632514097"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W1992908141","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W217710954","https://openalex.org/W2395719637"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"iterative":[3],"algorithm":[4,59],"to":[5],"extract":[6],"the":[7,38,44,48,58,62,73,85],"voice":[8,49,75],"source":[9,50,76],"waveform":[10],"from":[11],"recordings":[12],"of":[13,28,98],"speech":[14],"for":[15],"speaker":[16,100],"identification.":[17],"The":[18],"method":[19],"detects":[20],"glottal":[21,29,45,56],"closings,":[22],"then":[23],"constructs":[24],"a":[25,79,90,96],"speaker-dependent":[26],"library":[27],"pulse":[30],"waveforms":[31],"by":[32],"clustering":[33],"data":[34,87],"windows":[35],"centered":[36],"on":[37],"linear":[39],"prediction":[40],"error":[41,102],"time-series":[42],"at":[43],"closures.":[46],"With":[47],"modeled":[51],"as":[52],"scaled":[53],"and":[54,89],"shifted":[55],"pulses,":[57],"iteratively":[60],"determines":[61],"vocal":[63],"tract":[64],"parameters":[65],"in":[66],"each":[67],"frame.":[68],"In":[69],"experiments,":[70],"we":[71,94],"combine":[72],"extracted":[74],"information":[77],"with":[78],"universal":[80],"background":[81],"model":[82],"(UBM).":[83],"Using":[84],"TIMIT":[86],"corpus":[88],"200-speaker":[91],"population":[92],"size,":[93],"demonstrate":[95],"factor":[97],"three":[99],"recognition":[101],"reduction.":[103]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}