{"id":"https://openalex.org/W116024930","doi":"https://doi.org/10.21437/interspeech.2007-172","title":"Duration and pronunciation conditioned lexical modeling for speaker verification","display_name":"Duration and pronunciation conditioned lexical modeling for speaker verification","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W116024930","doi":"https://doi.org/10.21437/interspeech.2007-172","mag":"116024930"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-172","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":"https://orcid.org/0009-0008-7740-2557"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin Kajarekar","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kajarekar","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2049","last_page":"2052"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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":0.9937999844551086,"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/pronunciation","display_name":"Pronunciation","score":0.8248684406280518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8044700026512146},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7779642343521118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7121899127960205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5639392137527466},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5331943035125732},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4848262071609497},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4715331196784973},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4450666606426239},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4396282434463501},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41762515902519226},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4175381660461426},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2343517541885376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09736314415931702}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8248684406280518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044700026512146},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7779642343521118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7121899127960205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5639392137527466},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5331943035125732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4848262071609497},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4715331196784973},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4450666606426239},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4396282434463501},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41762515902519226},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4175381660461426},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2343517541885376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09736314415931702},{"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:10.21437/interspeech.2007-172","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W137729575","https://openalex.org/W205402702","https://openalex.org/W1488095445","https://openalex.org/W1535817944","https://openalex.org/W1538905335","https://openalex.org/W2002919652","https://openalex.org/W2078953162","https://openalex.org/W2141279928","https://openalex.org/W2144158639","https://openalex.org/W2153849757","https://openalex.org/W2165880886","https://openalex.org/W2401582030"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2129812225","https://openalex.org/W2112059504","https://openalex.org/W4290708361","https://openalex.org/W2727729836"],"abstract_inverted_index":{"We":[0,87],"propose":[1],"a":[2,82,92],"method":[3,65],"to":[4],"improve":[5],"speaker":[6,85,97],"recognition":[7,98],"lexical":[8,17,28,71],"model":[9,18],"performance":[10],"using":[11,21,55],"acoustic-prosodic":[12],"information.":[13],"More":[14],"specifically,":[15],"the":[16,67],"is":[19,91],"trained":[20],"durationand":[22],"pronunciation-conditioned":[23],"word":[24,69],"N-grams,":[25],"simultaneously":[26],"modeling":[27,43],"information":[29,78],"along":[30],"with":[31,46,81],"their":[32],"acoustic":[33,84],"and":[34,44],"prosodic":[35],"characteristics.":[36],"Support":[37],"vector":[38],"machines":[39],"are":[40],"used":[41],"for":[42],"scoring,":[45],"N-gram":[47],"frequency":[48],"vectors":[49],"serving":[50],"as":[51],"features.":[52,106],"Experimental":[53],"results":[54],"NIST":[56],"Speaker":[57],"Recognition":[58],"Evaluation":[59],"data":[60],"sets":[61],"show":[62],"that":[63,89,100],"this":[64,90],"outperforms":[66],"regular":[68],"N-gram-based":[70],"models.":[72],"Furthermore,":[73],"our":[74],"approach":[75],"gives":[76],"additional":[77],"when":[79],"combined":[80],"high-accuracy":[83],"model.":[86],"believe":[88],"promising":[93],"step":[94],"toward":[95],"integrated":[96],"models":[99],"combine":[101],"multiple":[102],"types":[103],"of":[104],"high-level":[105]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}