… In this paper RNN trained LSTM with graph structure has been proposed as a classification
model for PD detection. The classification accuracy is further improved by ADAM optimizer …

… (LSTMGIN) is proposed, which applies Graph Isomorphism Network (GIN) on LSTM outputs
for … In our LSTM-GIN model, speech signals are represented as graph-structured data so that …

… large vocabulary conversational speech recognition (LVCSR) … alignment of the speech
signal and training transcriptions. … LSTM is a special version of an RNN with memory cells that …

… deep learning model which fuses graph convolutional neural network (GCNN) … (LSTM).
In the fusion model, multiple GCNNs are applied to extract graph domain features while LSTM …

… and scalable way to represent data is in the form of graphs. Following the theory of graph
signal processing, we propose to model speech signal as a cycle graph or a line graph. Such …

… -LSTM-DNN: This structure applies convolutional neural network (CNN) to extract features
from the speech signal, followed by a LSTM … the global information from LSTM. The model was …

… a speech BCI based assistive technology for silent speech interface that recognizes data from
the measure of a user’s brain signals … thinking and speaking state using the EEG signals. …

… Long Short-Term Memory (LSTM) method for visual speech recognition. Finally, integrate
the … the graph is epoch versus accuracy. This graph shows the training and validation graph. …

… For evaluation of the proposed hybrid VAD system, we used a speech dataset which includes
speech signals acquired in a clean/silent environment (the sound-proof room) to eliminate …

… speech intelligibility level in this latter case. Starting from our previous work, a non-intrusive
system based on LSTM … From the analysis of these graphs, it can be observed that, although …