Generative AI has demonstrated impressive performance in various fields, among which speech synthesis is an interesting direction.With the diffusion model as the most popular generative model, numerous works have attempted two active tasks: text to speech and speech enhancement. This work conducts a survey on audio diffusion model, which is complementary to existing surveys that either lack the recent progress of diffusion-based speech synthesis or highlight an overall picture of applying diffusion model in multiple fields. Specifically, this work first briefly introduces the background of audio and diffusion model. As for the text-to-speech task, we divide the methods into three categories based on the stage where diffusion model is adopted: acoustic model, vocoder and end-to-end framework. Moreover, we categorize various speech enhancement tasks by either certain signals are removed or added into the input speech. Comparisons of experimental results and discussions are also covered in this survey.
Gladiolus is an important cut flower in the world, and its preference in Pakistan is next to roses. But the main problem that occurs in gladiolus is that it has short vase life. The present experiment was conducted with an objective to investigate the effect of four preservative solutions [distilled water, Sucrose (3%), AgNO3 (250 ppm), AgNO3 (250 ppm) + Sucrose (3%)] and packaging material on postharvest quality of three gladiolus varieties, “Tissue, White Prosperity and Alexandra”. Packaging material consists of control treatment (without packaging), packaging of cut spikes with 100 ppm acetic acid soaked cotton and packaging of polyethylene sheet after sucrose pulsing. The experiment was arranged as two factorial laid out according to completely randomized design (CRD) having three replications. Results showed that preservative solution having combination of AgNO3 (250 ppm) + Sucrose (3%) significantly improves days to open basal floret, floret opening percentage (%), bloom spread (inch), floret length (inch), floret diameter (inch), fresh spike weight (g), dry spike weight (g), fresh weight loss (%) and vase life (days). Moreover, this treatment was also effective in reducing the wilting (%) in all gladiolus varieties. However, for solution uptake (mL/spike) and solution balance (ml/spike), AgNO3 (250 ppm)alone gives the best results. For packaging treatment, the pulsing of a cut spike with 20% sucrose followed by polyethylene sheet wrapping proves to be effective. Among the varieties, Alexandra performed better for all quality parameters in comparison to White Prosperity and Tissue
Swarm intelligence has been applied to replicate numerous natural processes and relatively simple species to achieve excellent performance in a variety of disciplines. An autonomous approach employing deep reinforcement learning is presented in this study for swarm navigation. In this approach, complex 3D environments with static and dynamic obstacles and resistive forces such as linear drag, angular drag, and gravity are modeled to track multiple dynamic targets. In this regard, a novel island policy optimization model is introduced to tackle multiple dynamic targets simultaneously and thus make the swarm more dynamic. Moreover, new reward functions for robust swarm formation and target tracking are devised to learn complex swarm behaviors. Since the number of agents is not fixed and has only the partial observance of the environment, swarm formation and navigation become challenging. In this regard, the proposed strategy consists of four main components to tackle the aforementioned challenges: 1) Island policy-based optimization framework with multiple targets tracking 2) Novel reward functions for multiple dynamic target tracking 3) Improved policy and critic-based framework for the dynamic swarm management 4) Memory. The dynamic swarm management phase translates basic sensory input to highlevel commands and thus enhances swarm navigation and decentralized setup while maintaining the swarm's size fluctuations. While in the island model, the swarm can split into individual sub-swarms according to the number of targets, thus allowing it to track multiple targets that are far apart. Also, when multiple targets come close to each other, these sub-swarms have the ability to rejoin and thus form a single swarm surrounding all the targets. Customized state-of-the-art policy-based deep reinforcement learning neuroarchitectures are employed to achieve policy optimization. The results show that the proposed strategy enhances swarm navigation and can track multiple static and dynamic targets in complex environments.
This work covers the research work on decentralization of Online Social Networks (OSNs), issues with centralized design are studied with possible decentralized solutions. Centralized architecture is prone to privacy breach, p2p architecture for data and thus authority decentralization with encryption seems a possible solution. OSNs' users grow exponentially causing scalability issue, a natural solution is decentralization where users bring resources with them via personal machines or paid services. Also centralized services are not available unremittingly, to this end decentralization proposes replication. Decentralized solutions are also proposed for reliability issues arising in centralized systems and the potential threat of a central authority. Yet key to all problems isn't found, metadata may be enough for inferences about data and network traffic flow can lead to information on users' relationships. First issue can be mitigated by data padding or splitting in uniform blocks. Caching, dummy traffic or routing through a mix of nodes can be some possible solutions to the second.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.