In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement masking, 2) local conditioning of text and pitch to the superresolution network, and 3) conditional adversarial training. The proposed system consists of two main modules; a mel-synthesis network that generates a mel-spectrogram from the given input information, and a super-resolution network that upsamples the generated mel-spectrogram into a linear-spectrogram. In the mel-synthesis network, phonetic enhancement masking is applied to generate implicit formant masks solely from the input text, which enables a more accurate phonetic control of singing voice. In addition, we show that two other proposed methods -local conditioning of text and pitch, and conditional adversarial training -are crucial for a realistic generation of the human singing voice in the super-resolution process. Finally, both quantitative and qualitative evaluations are conducted, confirming the validity of all proposed methods.

Purpose To characterize intratumoral spatial heterogeneity at perfusion magnetic resonance (MR) imaging and investigate intratumoral heterogeneity as a predictor of recurrence-free survival (RFS) in breast cancer. Materials and Methods In this retrospective study, a discovery cohort (n = 60) and a multicenter validation cohort (n = 186) were analyzed. Each tumor was divided into multiple spatially segregated, phenotypically consistent subregions on the basis of perfusion MR imaging parameters. The authors first defined a multiregional spatial interaction (MSI) matrix and then, based on this matrix, calculated 22 image features. A network strategy was used to integrate all image features and classify patients into different risk groups. The prognostic value of imaging-based stratification was evaluated in relation to clinical-pathologic factors with multivariable Cox regression. Results Three intratumoral subregions with high, intermediate, and low MR perfusion were identified and showed high consistency between the two cohorts. Patients in both cohorts were stratified according to network analysis of multiregional image features regarding RFS (log-rank test, P = .002 for both). Aggressive tumors were associated with a larger volume of the poorly perfused subregion as well as interaction between poorly and moderately perfused subregions and surrounding parenchyma. At multivariable analysis, the proposed MSI-based marker was independently associated with RFS (hazard ratio: 3.42; 95% confidence interval: 1.55, 7.57; P = .002) adjusting for age, estrogen receptor (ER) status, progesterone receptor status, human epidermal growth factor receptor type 2 (HER2) status, tumor volume, and pathologic complete response (pCR). Furthermore, imaging helped stratify patients for RFS within the ER-positive and HER2-positive subgroups (log-rank test, P = .007 and .004) and among patients without pCR after neoadjuvant chemotherapy (log-rank test, P = .003). Conclusion Breast cancer consists of multiple spatially distinct subregions. Imaging heterogeneity is an independent prognostic factor beyond traditional risk predictors.

Remote sensing of individual tree species has many applications in resource management, biodiversity assessment and conservation. Airborne remote sensing using LiDAR and hyperspectral sensors has been used extensively to extract biophysical traits of vegetation and to detect species. However, its application for individual tree mapping remains limited due to the technical challenges of precise co-alignment of images acquired from different sensors and accurately delineating individual tree crowns (ITCs). In this study we developed a generic workflow to map tree species at ITC-level from hyperspectral imagery and LiDAR data using a combination of well-established and recently developed techniques. The workflow uses a non-parametric image registration approach to co-align images, a multi-class normalised graph cut method for ITC delineation, robust principal component analysis for feature extraction, and support vector machine for species classification. This workflow allows us to automatically map tree species at both pixel-and ITC-level. Experimental tests of the technique were conducted using ground data collected from a fully-mapped temperate woodland in the UK. The overall accuracy of pixel-level classification was 91%, while that of ITC-level classification was 61%. The test results demonstrate the effectiveness of the approach, and in particular the use of robust PCA to prune the hyperspectral dataset and reveal subtle difference among species.

Developing a robust algorithm for automatic individual tree crown (ITC) detection from laser scanning datasets is important for tracking the responses of trees to anthropogenic change. Such approaches allow the size, growth and mortality of individual trees to be measured, enabling forest carbon stocks and dynamics to be tracked and understood. Many algorithms exist for structurally simple forests including coniferous forests and plantations. Finding a robust solution for structurally complex, species-rich tropical forests remains a challenge; existing segmentation algorithms often perform less well than simple area-based approaches when estimating plot-level biomass. Here we describe a Multi-Class Graph Cut (MCGC) approach to tree crown delineation.This uses local three-dimensional geometry and density information, alongside knowledge of crown allometries, to segment individual tree crowns from LiDAR point clouds. Our approach robustly identifies trees in the top and intermediate layers of the canopy, but cannot recognise small trees. From these three-dimensional crowns, we are able to measure individual tree biomass. Comparing these estimates to those from permanent inventory plots, our algorithm is able to produce robust estimates of hectare-scale carbon density, demonstrating the power of ITC approaches in monitoring forests. The flexibility of our method to add additional dimensions of Preprint submitted to IEEE. c 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.information, such as spectral reflectance, make this approach an obvious avenue for future development and extension to other sources of three-dimensional data, such as structure from motion datasets. IntroductionAutomatically identifying and mapping trees is a long-standing goal within the field of forest remote sensing, and there is currently particular interest in finding robust solutions for segmenting multi-species stands with complex structures. 1-6 With the widespread adoption of Light Detection and Ranging (LiDAR) it is possible to collect data on the three-dimensional (3D) structure of forest stands over hundreds of square kilometers in a matter of hours, commonly in the form of 3D point clouds, 7-9 from which individual trees can be segmented. Individual tree approaches have the potential to track individual-level changes in response to events such as disease, biological invasion, logging and extreme climatic events (e.g. droughts) thereby gaining a clearer understanding of the processes that generate structural change. [10][11][12][13] Until recently, most approaches to delineating individual tree crowns (ITCs) relied on converting the 3D structural information contained in LiDAR datasets into rasterised 2D surfa...

Neurovascular coupling (NVC), the interaction between neural activity and vascular response, ensures normal brain function by maintaining brain homeostasis. We previously reported altered cerebrovascular responses during functional hyperemia in chronically stressed animals. However, the underlying neuronal-level changes associated with those hemodynamic changes remained unclear. Here, using in vivo and ex vivo experiments, we investigate the neuronal origins of altered NVC dynamics under chronic stress conditions in adult male mice. Stimulus-evoked hemodynamic and neural responses, especially beta and gamma-band local field potential activity, were significantly lower in chronically stressed animals, and the NVC relationship, itself, had changed. Further, using acute brain slices, we discovered that the underlying cause of this change was dysfunction of neuronal nitric oxide synthase (nNOS)-mediated vascular responses. Using FISH to check the mRNA expression of several GABAergic subtypes, we confirmed that only nNOS mRNA was significantly decreased in chronically stressed mice. Ultimately, chronic stress impairs NVC by diminishing nNOS-mediated vasodilation responses to local neural activity. Overall, these findings provide useful information in understanding NVC dynamics in the healthy brain. More importantly, this study reveals that impaired nNOS-mediated NVC function may be a contributory factor in the progression of stress-related diseases.