{"id":"https://openalex.org/W1760805220","doi":"https://doi.org/10.21437/interspeech.2004-511","title":"Unseen handset mismatch compensation based on a priori knowledge interpolation for robust speaker recognition","display_name":"Unseen handset mismatch compensation based on a priori knowledge interpolation for robust speaker recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1760805220","doi":"https://doi.org/10.21437/interspeech.2004-511","mag":"1760805220"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-511","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5058829808","display_name":"Jyh\u2010Her Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jyh-Her Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["National Taipei University of Technology"],"affiliations":[{"raw_affiliation_string":"National Taipei University of Technology","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058829808"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2858,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55216391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1769","last_page":"1772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9915000200271606,"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/handset","display_name":"Handset","score":0.9524669647216797},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7477269172668457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7279493808746338},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6502165794372559},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6187835931777954},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5920482873916626},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.5069432258605957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016021728515625},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4327000379562378},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3243352770805359},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1260451078414917}],"concepts":[{"id":"https://openalex.org/C2779971919","wikidata":"https://www.wikidata.org/wiki/Q1378949","display_name":"Handset","level":2,"score":0.9524669647216797},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7477269172668457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279493808746338},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6502165794372559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6187835931777954},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5920482873916626},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.5069432258605957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016021728515625},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4327000379562378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3243352770805359},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1260451078414917},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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:10.21437/interspeech.2004-511","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.408.4180","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.408.4180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isca-speech.org/archive_open/archive_papers/iscslp2004/096.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W95717433","https://openalex.org/W175297027","https://openalex.org/W2049633694","https://openalex.org/W2059857061","https://openalex.org/W2146871184","https://openalex.org/W2161804528","https://openalex.org/W2162125266","https://openalex.org/W2165880886","https://openalex.org/W2167152389"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Unseen":[0],"but":[1],"mismatch":[2],"handset":[3,22],"is":[4,33,92],"the":[5,41,48,74],"major":[6],"source":[7],"of":[8],"performance":[9],"degradation":[10],"for":[11,88,97],"speaker":[12,76,99],"recognition":[13,77],"in":[14,39],"telecommunication":[15],"environment.":[16],"In":[17],"this":[18],"paper,":[19],"an":[20],"unseen":[21],"characteristics":[23],"estimation":[24],"method":[25,96],"based":[26],"on":[27,69],"a":[28,94],"priori":[29],"knowledge":[30],"interpolation":[31],"(AKI)":[32],"proposed.":[34],"AKI":[35],"could":[36,79],"be":[37,80],"applied":[38],"both":[40],"feature":[42,49],"and":[43,50,59],"model":[44,51],"space":[45],"to":[46,85],"interpolate":[47],"transformation":[52],"functions":[53],"measured":[54],"using":[55],"stochastic":[56],"matching":[57],"(SM)":[58],"maximum":[60],"likelihood":[61],"linear":[62],"regression":[63],"(MLLR),":[64],"respectively.":[65],"Cross-validation":[66],"experimental":[67],"results":[68],"HTIMIT":[70],"database":[71],"showed":[72],"that":[73],"average":[75],"rate":[78],"improved":[81],"from":[82],"59.6%/57.8":[83],"%":[84,87],"73.8%/66.8":[86],"seen/unseen":[89],"handsets.":[90],"It":[91],"therefore":[93],"promising":[95],"robust":[98],"recognition.":[100],"1.":[101]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}