In real-world situations, speech reaching our ears is commonly corrupted by both room reverberation and background noise. These distortions are detrimental to speech intelligibility and quality, and also pose a serious problem to many speech-related applications, including automatic speech and speaker recognition. In order to deal with the combined effects of noise and reverberation, we propose a two-stage strategy to enhance corrupted speech, where denoising and dereverberation are conducted sequentially using deep neural networks. In addition, we design a new objective function that incorporates clean phase during model training to better estimate spectral magnitudes, which would in turn yield better phase estimates when combined with iterative phase reconstruction. The two-stage model is then jointly trained to optimize the proposed objective function. Systematic evaluations and comparisons show that the proposed algorithm improves objective metrics of speech intelligibility and quality substantially, and significantly outperforms previous one-stage enhancement systems.
This article describes an application of the Communities Advancing Resilience Toolkit (CART) Assessment Survey which has been recognized as an important community tool to assist communities in their resilience-building efforts. Developed to assist communities in assessing their resilience to disasters and other adversities, the CART survey can be used to obtain baseline information about a community, to identify relative community strengths and challenges, and to re-examine a community after a disaster or post intervention. This article, which describes an application of the survey in a community of 5 poverty neighborhoods, illustrates the use of the instrument, explicates aspects of community resilience, and provides possible explanations for the results. The paper also demonstrates how a community agency that serves many of the functions of a broker organization can enhance community resilience. Survey results suggest various dimensions of community resilience (as represented by core CART community resilience items and CART domains) and potential predictors. Correlates included homeownership, engagement with local entities/activities, prior experience with a personal emergency or crisis while living in the neighborhood, and involvement with a community organization that focuses on building safe and caring communities through personal relationships. In addition to influencing residents' perceptions of their community, it is likely that the community organization, which served as a sponsor for this application, contributes directly to community resilience through programs and initiatives that enhance social capital and resource acquisition and mobilization.
In the real world, speech is usually distorted by both reverberation and background noise. In such conditions, speech intelligibility is degraded substantially, especially for hearing-impaired (HI) listeners. As a consequence, it is essential to enhance speech in the noisy and reverberant environment. Recently, deep neural networks have been introduced to learn a spectral mapping to enhance corrupted speech, and shown significant improvements in objective metrics and automatic speech recognition score. However, listening tests have not yet shown any speech intelligibility benefit. In this paper, we propose to enhance the noisy and reverberant speech by learning a mapping to reverberant target speech rather than anechoic target speech. A preliminary listening test was conducted, and the results show that the proposed algorithm is able to improve speech intelligibility of HI listeners in some conditions. Moreover, we develop a masking-based method for denoising and compare it with the spectral mapping method. Evaluation results show that the maskingbased method outperforms the mapping-based method.Index Terms-speech intelligibility test, speech denoising, spectral mapping, ideal ratio mask, deep neural networks
The Surface Water and Ocean Topography (SWOT) satellite mission will, for the first time, provide simultaneous, high‐resolution measurements of water surface elevation and extent. Here we explore the applicability of SWOT's unique sampling to capture discharge frequency behavior throughout the Mississippi River Basin. Our findings suggest the mission may capture key variability in river discharge series. SWOT orbit specifications, US Geological Survey (USGS) discharge measurements, and potential uncertainty estimates are used to generate SWOT‐like river discharges. Frequency distributions and specific quantiles derived from synthetic SWOT discharge series are compared to those derived from daily USGS discharge series. Based on the Kolmogorov‐Smirnov test, SWOT temporal sampling has essentially no impact on derived frequency distributions. When including potential uncertainty, 78% of derived distributions are statistically identical. The combined effects of temporal sampling and discharge uncertainty mitigates the negative bias used for SWOT discharge uncertainty at larger discharge quantiles (i.e., ≥75% quantiles).
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.