By considering the nonlinear and dynamic dependency relationships between articulatory movements and acoustic signals, this study adopts bidirectional long short-term memory (BLSTM) based recurrent neural networks (RNN) for the articulatory-to-acoustic conversion.
By incorporating and utilizing multi-spectral, multi-temporal and spatial information in remote sensing images and considering the inherit spatial and sequential interdependence among neighboring pixels, we propose a new patch-based recurrent neural network (PB-RNN) systailoredored for classifying multi-temporal remote sensing data.
First, a memristor-based recurrent neural network is designed.
H state (k) and H observation (k) can be separately represented by two FNNs to build up a state-space-based recurrent neural network [18] for fitting the true mapping process.
The proposed model is tested with the English AMI speech recognition dataset and outperforms the baseline n-gram model, the basic recurrent neural network language models (RNNLM) and the GPU-based recurrent neural network language models (CUED-RNNLM) in perplexity and word error rate.
The results show that the proposed token-based recurrent neural network language model has outperformed the n-gram LM by approximately 3% and enhances the basic RNNLM and its GPU version CUED-RNNLM by approximately 1.5% when using the English AMI meeting corpus dataset.
A dynamic model, based on recurrent neural network (RNN), was developed to describe the growth of L. monocytogenes as a function of temperature and fluctuating conditions of acid pH, alkaline pH and concentration of NaCl.
A novel method named wavelet packet transform based Elman recurrent neural network (WPTERNN) was applied to differential pulse voltammetric techniques for simultaneous determination of Ni II), Zn II) and Co II) by combining wavelet packet denoising with Elman recurrent neural network (ERNN).
To understand why NCM TAIV) exhibited higher immunogenicity than NCM, NCM TA) and NCM IV), we used an immunoinformatic method to predict the continuous B-cell epitopes on MPER based on recurrent neural network [32].
The control scheme is based on recurrent neural networks emulator and controller with decoupled adaptive rates.
We proposed the first models based on recurrent neural networks (more specifically Long Short-Term Memory - LSTM) for classifying relations from clinical notes.
