scholarly journals Performance Analysis and Recognition of Speech using Recurrent Neural Network

2019 ◽  
Vol 1 (1) ◽  
pp. 87-95
Author(s):  
Bishon Lamichanne ◽  
Hari K.C.
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Performance Analysis ◽  
Recurrent Neural Network ◽  
Error Rate ◽  
English Language ◽  
Daily Lives ◽  
Crucial Step ◽  
The Neural Network ◽  
Positive Results

Speech is one of the most natural ways to communicate between people. It plays an important role in our daily lives. To make machines able to talk with people is a challenging but very useful task. A crucial step is to enable machines to recognize and understand what people are saying. Hence, speech recognition becomes a key technique providing an interface for communication between machines and humans. There has been a long research history on speech recognition. Neural network is known as a technique that has ability to classify nonlinear problem. Today, lots of research are going in the field of speech recognition with the help of the Neural Network. Even though positive results have been obtained from continuous study, research on minimizing the error rate is still gaining lots attention. The English language offers a number of challenges for speech recognition. This paper implements the RNN to analyze and recognize speech from the set of spoken words.

scholarly journals Research on Speaker Recognition of DRNN in Different Noise Environment

2020 ◽  
Author(s):  
chaofeng lan ◽  
yuanyuan Zhang ◽  
hongyun Zhao
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Recurrent Neural Network ◽  
Speaker Recognition ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Noisy Environment ◽  
Signal To Noise ◽  
Noise Ratio ◽  
Improved Model

Abstract This paper draws on the training method of Recurrent Neural Network (RNN), By increasing the number of hidden layers of RNN and changing the layer activation function from traditional Sigmoid to Leaky ReLU on the input layer, the first group and the last set of data are zero-padded to enhance the effective utilization of data such that the improved reduction model of Denoise Recurrent Neural Network (DRNN) with high calculation speed and good convergence is constructed to solve the problem of low speaker recognition rate in noisy environment. According to this model, the random semantic speech signal with a sampling rate of 16 kHz and a duration of 5 seconds in the speech library is studied. The experimental settings of the signal-to-noise ratios are − 10dB, -5dB, 0dB, 5dB, 10dB, 15dB, 20dB, 25dB. In the noisy environment, the improved model is used to denoise the Mel Frequency Cepstral Coefficients (MFCC) and the Gammatone Frequency Cepstral Coefficents (GFCC), impact of the traditional model and the improved model on the speech recognition rate is analyzed. The research shows that the improved model can effectively eliminate the noise of the feature parameters and improve the speech recognition rate. When the signal-to-noise ratio is low, the speaker recognition rate can be more obvious. Furthermore, when the signal-to-noise ratio is 0dB, the speaker recognition rate of people is increased by 40%, which can be 85% improved compared with the traditional speech model. On the other hand, with the increase in the signal-to-noise ratio, the recognition rate is gradually increased. When the signal-to-noise ratio is 15dB, the recognition rate of speakers is 93%.

scholarly journals Where to put the image in an image caption generator

2018 ◽  
Vol 24 (3) ◽  
pp. 467-489 ◽  
Author(s):  
MARC TANTI ◽  
ALBERT GATT ◽  
KENNETH P. CAMILLERI
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
State Vector ◽  
Language Model ◽  
Image Features ◽  
Subsequent Stage ◽  
Multimodal Integration ◽  
The Neural Network ◽  
Large Memory ◽  
Image Caption

AbstractWhen a recurrent neural network (RNN) language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN – conditioning the language model by ‘injecting’ image features – or in a layer following the RNN – conditioning the language model by ‘merging’ image features. While both options are attested in the literature, there is as yet no systematic comparison between the two. In this paper, we empirically show that it is not especially detrimental to performance whether one architecture is used or another. The merge architecture does have practical advantages, as conditioning by merging allows the RNN’s hidden state vector to shrink in size by up to four times. Our results suggest that the visual and linguistic modalities for caption generation need not be jointly encoded by the RNN as that yields large, memory-intensive models with few tangible advantages in performance; rather, the multimodal integration should be delayed to a subsequent stage.

Sign in / Sign up

Export Citation Format

Share Document