In this paper, we present a new on-device automatic speech recognition (ASR) system based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) corpus. We attained around 90% of a word recognition rate for general domain mainly by using joint training of connectionist temporal classifier (CTC) and cross entropy (CE) losses, minimum word error rate (MWER) training, layer-wise pretraining and data augmentation methods. In addition, we compressed our models by more than 3.4 times smaller using an iterative hyper low-rank approximation (LRA) method while minimizing the degradation in recognition accuracy. The memory footprint was further reduced with 8-bit quantization to bring down the final model size to lower than 39 MB. For on-demand adaptation, we fused the MoChA models with statistical n-gram models, and we could achieve a relatively 36% improvement on average in word error rate (WER) for target domains including the general domain.
Studies suggest that time-restricted feeding (TRF) may prevent obesity and its commodities. At present, little is known about how TRF impacts immune cells, and whether such an effect is linked to altered metabolic parameters under condition of a high-fat diet (HFD)-induced obesity. To address these issues, we conducted a study in which we determined whether TRF has therapeutic efficacy against weight gain, adiposity, as well as associated immune cell disturbance found in obese mice. Six-week-old male C57BL/6 mice were fed a low-fat diet (LFD) or HFD ad libitum for six weeks, after which time a subgroup of HFD mice was switched to the 10 h TRF paradigm (HFD-TRF) for additional eight weeks. We found that TRF intervention reduced HFD-induced weight gain. Even with comparable fat mass and mean adipocyte area, the HFD-TRF group had lower mRNA levels of proinflammatory cytokine Tnfα and chemokine Ccl8, along with reduced numbers of adipose tissue macrophages (ATM), CD11c+ ATM, and CD8+ T cell compared to the HFD group, while maintaining CD8+ to CD4+ ratio at levels similar to those in the LFD group. Furthermore, TRF intervention was effective in improving glucose tolerance and reducing HOMA-IR. Taken together, our findings suggest that TRF restores the obesity-induced alteration in immune cell composition, and this effect may in part contribute to health benefits (including insulin sensitivity) of practicing TRF.
A power-constrained contrast-enhancement algorithm for emissive displays based on histogram equalization (HE) is proposed in this paper. We first propose a log-based histogram modification scheme to reduce overstretching artifacts of the conventional HE technique. Then, we develop a power-consumption model for emissive displays and formulate an objective function that consists of the histogram-equalizing term and the power term. By minimizing the objective function based on the convex optimization theory, the proposed algorithm achieves contrast enhancement and power saving simultaneously. Moreover, we extend the proposed algorithm to enhance video sequences, as well as still images. Simulation results demonstrate that the proposed algorithm can reduce power consumption significantly while improving image contrast and perceptual quality.
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.