Abstract:The Laplace distribution is one of the earliest distributions in probability theory and is a frequently used distribution in many fields. Consequently, various goodness-of-fit tests for the Laplace distribution have been thoroughly derived in theliterature. The purpose of this paper is to carry out a comparative study of these tests as well as a new one we develop. Power comparisons of all such tests are performed via Monte Carlo simulations of sample data generatedfrom twenty seven alternatives distributions.… Show more
“…The empirical data distributions seem to fit better the Laplacian distribution (i.e., solid red line) than the Gaussian distribution (i.e., blue dashed line). Table 2 summarizes the results of the Goodnessof-Fit test [53]. Let…”
Section: ) Experimental Validation Of Modeling Assumptionsmentioning
confidence: 99%
“…In addition to the evidence provided in Section V-A2, a comprehensive Goodness-of-Fit test [53] is performed to assess the approximation error between x E,l and H (f c ) θ in ( 14) for the LAD-P-MLE ENF estimation scheme, which is the most accurate framework in Table 4. The test is conducted for the first 5 audio recordings from the folder H1, resulting in a total of 2873 frames.…”
Section: ) Statistical Analysis Of the Approximation Errormentioning
The Electric Network Frequency (ENF) serves as a simple means to verify the authenticity of audio recordings. ENF variations contain crucial information, acting as a distinctive "fingerprint" when electronic devices are connected or located near power mains. A novel framework for ENF estimation is proposed. This approach alternates between the Least Absolute Deviation (LAD) regression for determining regression weights and objective function minimization with respect to frequency, adapting them within the context of the ℓ 1 norm or the sum of ℓ 1 norms of the approximation error. This framework is a direct consequence of Laplacian distributed noise. Goodness-of-fit tests are reported, indicating that the Laplacian noise hypothesis is more appropriate than the hypothesis of Gaussian noise in the benchmark ENF-WHU dataset. Extensive evaluation using audio recordings from the aforementioned dataset demonstrates the exceptional performance of the proposed framework outperforming state-of-the-art ENF estimation schemes. These findings provide compelling evidence for the efficacy of the proposed ENF estimation schemes as reliable prerequisites for detecting audio forgeries.
“…The empirical data distributions seem to fit better the Laplacian distribution (i.e., solid red line) than the Gaussian distribution (i.e., blue dashed line). Table 2 summarizes the results of the Goodnessof-Fit test [53]. Let…”
Section: ) Experimental Validation Of Modeling Assumptionsmentioning
confidence: 99%
“…In addition to the evidence provided in Section V-A2, a comprehensive Goodness-of-Fit test [53] is performed to assess the approximation error between x E,l and H (f c ) θ in ( 14) for the LAD-P-MLE ENF estimation scheme, which is the most accurate framework in Table 4. The test is conducted for the first 5 audio recordings from the folder H1, resulting in a total of 2873 frames.…”
Section: ) Statistical Analysis Of the Approximation Errormentioning
The Electric Network Frequency (ENF) serves as a simple means to verify the authenticity of audio recordings. ENF variations contain crucial information, acting as a distinctive "fingerprint" when electronic devices are connected or located near power mains. A novel framework for ENF estimation is proposed. This approach alternates between the Least Absolute Deviation (LAD) regression for determining regression weights and objective function minimization with respect to frequency, adapting them within the context of the ℓ 1 norm or the sum of ℓ 1 norms of the approximation error. This framework is a direct consequence of Laplacian distributed noise. Goodness-of-fit tests are reported, indicating that the Laplacian noise hypothesis is more appropriate than the hypothesis of Gaussian noise in the benchmark ENF-WHU dataset. Extensive evaluation using audio recordings from the aforementioned dataset demonstrates the exceptional performance of the proposed framework outperforming state-of-the-art ENF estimation schemes. These findings provide compelling evidence for the efficacy of the proposed ENF estimation schemes as reliable prerequisites for detecting audio forgeries.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.