Matches in SemOpenAlex for { <https://semopenalex.org/work/W2407170210> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2407170210 abstract "Speech synthesis and voice conversion techniques can pose threats to current speaker verification (SV) systems. For this purpose, it is essential to develop front end systems that are able to distinguish human speech vs. spoofed speech (synthesized or voice converted). In this paper, for the ASVspoof 2015 challenge, we propose a detector based on combination of cochlear filter cepstral coefficients (CFCC) and change in instantaneous frequency (IF), (i.e., CFCCIF) to detect natural vs. spoofed speech. The CFCCIF features were extracted at frame-level and Gaussian mixture model (GMM)based classification system was used. On the development set, the proposed features (i.e., CFCCIF) after fusion with Mel frequency cepstral coefficients (MFCC) features achieved an EER of 1.52 %, which is a significant reduction from MFCC (3.26 %) and CFCCIF (2.29 %) alone using 12-D static features. The EER further decreases to 0.89 % and 0.83 % for delta and delta-delta features, respectively. Experimental results on evaluation set show that fusion of MFCC and CFCCIF works relatively well with an EER of 0.41 % for known attacks and 2.013 % EER for unknown attacks. On an average, fusion of MFCC and CFCCIF features provided relatively best EER of 1.211 % for the challenge." @default.
- W2407170210 created "2016-06-24" @default.
- W2407170210 creator A5043002276 @default.
- W2407170210 creator A5071210435 @default.
- W2407170210 date "2015-09-06" @default.
- W2407170210 modified "2023-09-30" @default.
- W2407170210 title "Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech" @default.
- W2407170210 cites W1550612414 @default.
- W2407170210 cites W1586405805 @default.
- W2407170210 cites W1688416049 @default.
- W2407170210 cites W174866149 @default.
- W2407170210 cites W2061278248 @default.
- W2407170210 cites W2072473772 @default.
- W2407170210 cites W2100649345 @default.
- W2407170210 cites W2115755118 @default.
- W2407170210 cites W2117544888 @default.
- W2407170210 cites W2123299109 @default.
- W2407170210 cites W2129142580 @default.
- W2407170210 cites W2135049032 @default.
- W2407170210 cites W2171903461 @default.
- W2407170210 cites W2176804518 @default.
- W2407170210 cites W2186111442 @default.
- W2407170210 cites W2237024778 @default.
- W2407170210 cites W2405506115 @default.
- W2407170210 cites W344150399 @default.
- W2407170210 cites W8362967 @default.
- W2407170210 doi "https://doi.org/10.21437/interspeech.2015-467" @default.
- W2407170210 hasPublicationYear "2015" @default.
- W2407170210 type Work @default.
- W2407170210 sameAs 2407170210 @default.
- W2407170210 citedByCount "70" @default.
- W2407170210 countsByYear W24071702102016 @default.
- W2407170210 countsByYear W24071702102017 @default.
- W2407170210 countsByYear W24071702102018 @default.
- W2407170210 countsByYear W24071702102019 @default.
- W2407170210 countsByYear W24071702102020 @default.
- W2407170210 countsByYear W24071702102021 @default.
- W2407170210 countsByYear W24071702102022 @default.
- W2407170210 countsByYear W24071702102023 @default.
- W2407170210 crossrefType "proceedings-article" @default.
- W2407170210 hasAuthorship W2407170210A5043002276 @default.
- W2407170210 hasAuthorship W2407170210A5071210435 @default.
- W2407170210 hasConcept C100515483 @default.
- W2407170210 hasConcept C106131492 @default.
- W2407170210 hasConcept C151989614 @default.
- W2407170210 hasConcept C153180895 @default.
- W2407170210 hasConcept C154945302 @default.
- W2407170210 hasConcept C167900197 @default.
- W2407170210 hasConcept C28490314 @default.
- W2407170210 hasConcept C31258907 @default.
- W2407170210 hasConcept C31972630 @default.
- W2407170210 hasConcept C41008148 @default.
- W2407170210 hasConcept C52622490 @default.
- W2407170210 hasConcept C88485024 @default.
- W2407170210 hasConceptScore W2407170210C100515483 @default.
- W2407170210 hasConceptScore W2407170210C106131492 @default.
- W2407170210 hasConceptScore W2407170210C151989614 @default.
- W2407170210 hasConceptScore W2407170210C153180895 @default.
- W2407170210 hasConceptScore W2407170210C154945302 @default.
- W2407170210 hasConceptScore W2407170210C167900197 @default.
- W2407170210 hasConceptScore W2407170210C28490314 @default.
- W2407170210 hasConceptScore W2407170210C31258907 @default.
- W2407170210 hasConceptScore W2407170210C31972630 @default.
- W2407170210 hasConceptScore W2407170210C41008148 @default.
- W2407170210 hasConceptScore W2407170210C52622490 @default.
- W2407170210 hasConceptScore W2407170210C88485024 @default.
- W2407170210 hasLocation W24071702101 @default.
- W2407170210 hasOpenAccess W2407170210 @default.
- W2407170210 hasPrimaryLocation W24071702101 @default.
- W2407170210 hasRelatedWork W188159071 @default.
- W2407170210 hasRelatedWork W1996938627 @default.
- W2407170210 hasRelatedWork W2407170210 @default.
- W2407170210 hasRelatedWork W2546080374 @default.
- W2407170210 hasRelatedWork W2726823740 @default.
- W2407170210 hasRelatedWork W2836844603 @default.
- W2407170210 hasRelatedWork W2947297060 @default.
- W2407170210 hasRelatedWork W2952595417 @default.
- W2407170210 hasRelatedWork W3132878323 @default.
- W2407170210 hasRelatedWork W4210305678 @default.
- W2407170210 isParatext "false" @default.
- W2407170210 isRetracted "false" @default.
- W2407170210 magId "2407170210" @default.
- W2407170210 workType "article" @default.