An adaptive noise sensing method is proposed to improve the speech sensing performance of speech-based applications operated over wireless sensor networks. The proposed method is based on nonnegative matrix factorization (NMF), which consists of adaptive noise sensing and noise reduction. In other words, adaptive noise sensing is performed by adapting a priori noise basis matrix of the NMF, which is estimated from the noise signal, resulting in an adapted noise basis matrix. Subsequently, the adapted noise basis matrix is used for the NMF decomposition of noisy speech into clean speech and background noise. The estimated clean speech signal is then applied to a front-end of the speech-based applications. The performance of the proposed NMF-based noise sensing and reduction method is first evaluated by measuring the source to distortion ratio (SDR), the source to interferences ratio (SIR), and the source to artifacts ratio (SAR). In addition, the proposed method is applied to an automatic speech recognition (ASR) system, which is a typical speech-based application, and then the average word error rate (WER) of the ASR is compared with that employing either a Wiener filter, or a conventional NMF-based noise reduction method using only a priori noise basis matrix.
In this study, a self-administered checklist for evaluation of the musculoskeletal disorders risk factors in construction industry was developed, and its reliability and validity were studied. 10 items of the checklist were determined based on the literature review, and total 2,793 construction workers participated in the analysis of the checklist's applicability. The results from the reliability analysis showed high Cohen's kappa coefficient (0.50~0.77), and high validity was also obtained in terms of relative risk (RR 1.73~9.14). Positive predictability was relatively low (13.0~32.5%), while negative predictability was high (80.1~96.8%). It can be concluded that the checklist would be suitable as a quick filtering tool of the ergonomic risk factors.
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.