To obtain a speaker’s pronunciation characteristics, a method is proposed based on an idea from bionics, which uses spectrogram statistics to achieve a characteristic spectrogram to give a stable representation of the speaker’s pronunciation from a linear superposition of short-time spectrograms. To deal with the issue of slow network training and recognition speed for speaker recognition systems on resource-constrained devices, based on a traditional SOM neural network, an adaptive clustering self-organizing feature map SOM (AC-SOM) algorithm is proposed. This algorithm automatically adjusts the number of neurons in the competition layer based on the number of speakers to be recognized until the number of clusters matches the number of speakers. A 100-speaker database of characteristic spectrogram samples was built and applied to the proposed AC-SOM model, yielding a maximum training time of only 304 s, with a maximum sample recognition time of less than 28 ms. Comparing to other approaches, the proposed method offers greatly improved training and recognition speed without sacrificing too much recognition accuracy. The promising results suggest that the proposed method satisfies real-time data processing and execution requirements for edge intelligence systems better than other speaker recognition methods.
Mutualism between plants and animals demonstrates that grazing has positive impacts on plant growth. Animal saliva plays an important role in plant–herbivore interactions, and various salivary components work for the beneficial relationship. This study was performed to compare responses of Leymus chinensis (Trin.) Tzvelev. (Poaceae) to sheep saliva and two salivary components. One randomized block designed experiment was conducted in 2007 with six treatments: control, clipping with water, with saliva, with epidermal growth factor (EGF), with thiamine and with mixture of EGF and thiamine. There were significant differences between treatments on biomass, buds and tillers of L. chinensis. Compared with control plants, there was no compensatory response in clipped plants due to the limited number of available meristems in late‐growing season. Plants in clipping with saliva had more biomass and buds than those in clipping with water or salivary components. Clipping with salivary components had no stimulatory effects on plant growth, relative to clipping with water. The results showed that herbivore saliva had greater impacts than salivary components, and there was no additive effect between salivary components on plant growth. This study demonstrated the complexity in saliva components, which offer saliva with the capacity to play an important role in plant–herbivore interactions.
Currently, curve fitting has been widely used in data processing. Spiking Neural Network is used to provide fast and accurate curve fitting with discrete data in this paper. First, the principle of Spiking Neural Network is introduced. Second, the Spiking Neural Network for curve fitting based on the MATLAB simulation platform is established. Finally, curve fitting of a linear function and an exponential function are made. The average error values are 0 and 0.3, the results show that Spiking Neural Network can be used in curve fitting effectively.
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.