Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on deep neural networks, have recently emerged as potential alternatives to traditional unsupervised approaches and with sufficient training, can alleviate the shortcomings of the unsupervised methods in various real-life acoustic environments. In this light, we review recently developed, representative deep learning approaches for tackling non-stationary additive and convolutional degradation of speech with the aim of providing guidelines for those involved in the development of environmentally robust speech recognition systems. We separately discuss single-and multi-channel techniques developed for the front-end and back-end of speech recognition systems, as well as joint front-end and back-end training frameworks.

No abstract

Atopic dermatitis (AD) is a chronic recurrent skin disease dominated by T-helper 2 inflammation. Momelotinib (MMB) is a novel JAK1/JAK2 inhibitor suppressing the signal transduction of multiple pro-inflammatory cytokines. Recent studies indicated that JAK inhibitor could play a therapeutic role in AD disease. In this study, we evaluated the efficacy of MMB as a novel JAK1/JAK2 inhibitor in DNCB-induced AD mice and TSLP-activated dendritic cells. Our data showed that topical application of MMB reduced the skin severity scores and total serum IgE levels, and alleviated the histological indexes including epidermal thickness measurement and mast cell number. Also, it was demonstrated that MMB down-regulated the mRNA expression of IL-4, IL-5, IFN-γ and TSLP, and inhibited the phosphorylation of STAT1, STAT3 and STAT5 in skin lesions. Moreover, MMB reduced the expression of CD80, CD86, MHCII and mRNA of OX40L in TSLP-activated dendritic cells. In general, our study suggests that MMB can improve the symptoms of AD and topical application of MMB can become a promising new therapy strategy for AD.

Speech is a critical biomarker for Huntington Disease (HD), with changes in speech increasing in severity as the disease progresses. Speech analyses are currently conducted using either transcriptions created manually by trained professionals or using global rating scales. Manual transcription is both expensive and time-consuming and global rating scales may lack sufficient sensitivity and fidelity [1]. Ultimately, what is needed is an unobtrusive measure that can cheaply and continuously track disease progression. We present first steps towards the development of such a system, demonstrating the ability to automatically differentiate between healthy controls and individuals with HD using speech cues. The results provide evidence that objective analyses can be used to support clinical diagnoses, moving towards the tracking of symptomatology outside of laboratory and clinical environments.