FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964273407> ?p ?o ?g. }

• W2964273407 endingPage "1825" @default.
• W2964273407 startingPage "1815" @default.
• W2964273407 abstract "In this paper, we combine Hidden Markov Models (HMMs) with i-vector extractors to address the problem of text-dependent speaker recognition with random digit strings. We employ digit-specific HMMs to segment the utterances into digits, to perform frame alignment to HMM states and to extract Baum-Welch statistics. By making use of the natural partition of input features into digits, we train digit-specific i-vector extractors on top of each HMM and we extract well-localized i-vectors, each modelling merely the phonetic content corresponding to a single digit. We then examine ways to perform channel and uncertainty compensation, and we propose a novel method for using the uncertainty in the i-vector estimates. The experiments on RSR2015 part III show that the proposed method attains 1.52% and 1.77% Equal Error Rate (EER) for male and female respectively, outperforming state-of-the-art methods such as x-vectors, trained on vast amounts of data. Furthermore, these results are attained by a single system trained entirely on RSR2015, and by a simple score-normalized cosine distance. Moreover, we show that the omission of channel compensation yields only a minor degradation in performance, meaning that the system attains state-of-the-art results even without recordings from multiple handsets per speaker for training or enrolment. Similar conclusions are drawn from our experiments on the RedDots corpus, where the same method is evaluated on phrases. Finally, we report results with bottleneck features and show that further improvement is attained when fusing them with spectral features." @default.
• W2964273407 created "2019-07-30" @default.
• W2964273407 creator A5002474493 @default.
• W2964273407 creator A5024773257 @default.
• W2964273407 creator A5040042464 @default.
• W2964273407 creator A5061939508 @default.
• W2964273407 date "2019-11-01" @default.
• W2964273407 modified "2023-09-28" @default.
• W2964273407 title "Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors" @default.
• W2964273407 cites W1494198834 @default.
• W2964273407 cites W1589137271 @default.
• W2964273407 cites W1851243731 @default.
• W2964273407 cites W1996512145 @default.
• W2964273407 cites W2057038408 @default.
• W2964273407 cites W2064364374 @default.
• W2964273407 cites W2072254246 @default.
• W2964273407 cites W2137286467 @default.
• W2964273407 cites W2150769028 @default.
• W2964273407 cites W2166688768 @default.
• W2964273407 cites W2167768673 @default.
• W2964273407 cites W2333871989 @default.
• W2964273407 cites W2413096897 @default.
• W2964273407 cites W2479269803 @default.
• W2964273407 cites W2491474862 @default.
• W2964273407 cites W2498117901 @default.
• W2964273407 cites W2505121225 @default.
• W2964273407 cites W2516764878 @default.
• W2964273407 cites W2584329820 @default.
• W2964273407 cites W2590440273 @default.
• W2964273407 cites W2606778926 @default.
• W2964273407 cites W2612122134 @default.
• W2964273407 cites W2726515241 @default.
• W2964273407 cites W2747249235 @default.
• W2964273407 cites W2808631503 @default.
• W2964273407 cites W2888968865 @default.
• W2964273407 cites W2889519245 @default.
• W2964273407 cites W2890964092 @default.
• W2964273407 cites W2936028438 @default.
• W2964273407 cites W2938358845 @default.
• W2964273407 cites W2963371159 @default.
• W2964273407 cites W2963450999 @default.
• W2964273407 cites W2964351684 @default.
• W2964273407 cites W4234330420 @default.
• W2964273407 doi "https://doi.org/10.1109/taslp.2019.2928143" @default.
• W2964273407 hasPublicationYear "2019" @default.
• W2964273407 type Work @default.
• W2964273407 sameAs 2964273407 @default.
• W2964273407 citedByCount "11" @default.
• W2964273407 countsByYear W29642734072019 @default.
• W2964273407 countsByYear W29642734072020 @default.
• W2964273407 countsByYear W29642734072021 @default.
• W2964273407 countsByYear W29642734072022 @default.
• W2964273407 countsByYear W29642734072023 @default.
• W2964273407 crossrefType "journal-article" @default.
• W2964273407 hasAuthorship W2964273407A5002474493 @default.
• W2964273407 hasAuthorship W2964273407A5024773257 @default.
• W2964273407 hasAuthorship W2964273407A5040042464 @default.
• W2964273407 hasAuthorship W2964273407A5061939508 @default.
• W2964273407 hasBestOaLocation W29642734072 @default.
• W2964273407 hasConcept C127162648 @default.
• W2964273407 hasConcept C149635348 @default.
• W2964273407 hasConcept C153180895 @default.
• W2964273407 hasConcept C154945302 @default.
• W2964273407 hasConcept C23224414 @default.
• W2964273407 hasConcept C2780513914 @default.
• W2964273407 hasConcept C28490314 @default.
• W2964273407 hasConcept C2984784707 @default.
• W2964273407 hasConcept C31258907 @default.
• W2964273407 hasConcept C33923547 @default.
• W2964273407 hasConcept C40969351 @default.
• W2964273407 hasConcept C41008148 @default.
• W2964273407 hasConcept C50644808 @default.
• W2964273407 hasConcept C94375191 @default.
• W2964273407 hasConcept C94957134 @default.
• W2964273407 hasConceptScore W2964273407C127162648 @default.
• W2964273407 hasConceptScore W2964273407C149635348 @default.
• W2964273407 hasConceptScore W2964273407C153180895 @default.
• W2964273407 hasConceptScore W2964273407C154945302 @default.
• W2964273407 hasConceptScore W2964273407C23224414 @default.
• W2964273407 hasConceptScore W2964273407C2780513914 @default.
• W2964273407 hasConceptScore W2964273407C28490314 @default.
• W2964273407 hasConceptScore W2964273407C2984784707 @default.
• W2964273407 hasConceptScore W2964273407C31258907 @default.
• W2964273407 hasConceptScore W2964273407C33923547 @default.
• W2964273407 hasConceptScore W2964273407C40969351 @default.
• W2964273407 hasConceptScore W2964273407C41008148 @default.
• W2964273407 hasConceptScore W2964273407C50644808 @default.
• W2964273407 hasConceptScore W2964273407C94375191 @default.
• W2964273407 hasConceptScore W2964273407C94957134 @default.
• W2964273407 hasIssue "11" @default.
• W2964273407 hasLocation W29642734071 @default.
• W2964273407 hasLocation W29642734072 @default.
• W2964273407 hasOpenAccess W2964273407 @default.
• W2964273407 hasPrimaryLocation W29642734071 @default.
• W2964273407 hasRelatedWork W1030110109 @default.
• W2964273407 hasRelatedWork W115166522 @default.
• W2964273407 hasRelatedWork W1829432249 @default.
• W2964273407 hasRelatedWork W2128760193 @default.

• next