A comparative analysis of pooling strategies for convolutional neural network based Hindi ASR

Passricha, Vishal; Aggarwal, Rajesh

doi:10.1007/s12652-019-01325-y

Cited by 22 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. , R } is termed as a pooling shift which allows enabling overlap within concerning pooling regions when N < R. The biggest limitation of max pooling is that all the other items are ignored completely whereas only the biggest element from the pooling region is assessed [23]. If most of the components in the pooling region are of large magnitude, the distinguishing traits vanish once the max pooling process has been completed.…”

Section: Max Pooling Methodsmentioning

confidence: 99%

A Comparison of Pooling Methods for Convolutional Neural Networks

et al. 2022

View full text Add to dashboard Cite

One of the most promising techniques used in various sciences is deep neural networks (DNNs). A special type of DNN called a convolutional neural network (CNN) consists of several convolutional layers, each preceded by an activation function and a pooling layer. The feature map of the previous layer is sampled by the pooling layer (that seems to be an important layer) to create a new feature map with condensed resolution. This layer significantly reduces the spatial dimension of the input. It always accomplished two main goals. As a first step, it reduces the number of parameters or weights to minimize computational costs. The second step is to prevent the overfitting of the network. In addition, pooling techniques can significantly reduce model training time and computational costs. This paper provides a critical understanding of traditional and modern pooling techniques and highlights the strengths and weaknesses for readers. Moreover, the performance of pooling techniques on different datasets is qualitatively evaluated and reviewed. This study is expected to contribute to a comprehensive understanding of the importance of CNNs and pooling techniques in computer vision challenges.

show abstract

Section: Max Pooling Methodsmentioning

confidence: 99%

A Comparison of Pooling Methods for Convolutional Neural Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Authors found that MFCC is effective for end to end acoustic modelling using CNN [52], [53]. MFCC is widely used feature while considering speech modelling [54], [55]. MFCC based comparative study of speech recognition techniques was conducted by authors who found that MFCC with HMM gave recognition accuracy of 85 percent and with deep neural networks the score was 82.2 percent [56].…”

Section: аналіз мовленнєвих особливостей шкали мел з використанням електрографічних і мовних сигналів параметризованим методом Knn і Xgbomentioning

confidence: 99%

Analysis of the Mel Scale Features Using Electrography and Speech Signals by Parameterized KNN and Xgboost

Skuratovskyi¹,

Bazarna²

2021

INFORMATION TECHNOLOGY AND SOCIETY

View full text Add to dashboard Cite

“…With recent advances in deep learning showing highly impressive misclassification rate for image or audio-based processing [29], we aim to further push the lower bound of misprediction rates by applying deep learning algorithms to branch prediction. Deep learning [23] is a set of algorithms to train and utilize multi-layer neural networks.…”

Section: B Dnn and Dnn-based Predictor Modelsmentioning

confidence: 99%

“…Locally connected networks with the longest history bits [22], such as convolution neural networks (CNNs) [32], [33], are likely to be a better choice for branch prediction as most branches show high correlation with nearby history. CNNs [29], [34]- [38] are deep feedforward neural networks. The vital components of a CNN architecture are convolution layers and pooling layers, as shown in Fig.4.…”

Section: ) Cnn and Cnn-based Predictor Modelmentioning

confidence: 99%

Exploring Convolution Neural Network for Branch Prediction

et al. 2020

View full text Add to dashboard Cite

Recently, there have been significant advances in deep neural networks (DNNs) and they have shown distinctive performance in speech recognition, natural language processing, and image recognition. In this paper, we explore DNNs to push the limit for branch prediction. We treat branch prediction as a classification problem and employ both deep convolutional neural networks (CNNs), ranging from LeNet to ResNet-50, and deep belief network (DBN) for branch prediction. We compare the effectiveness of DNNs with the state-of-the-art branch predictors, including the perceptron, our prior work, Multi-poTAGE+SC, and MTAGE+SC branch predictors. The last two are the most recent winners of championship branch prediction (CBP) contests. Several interesting observations emerged from our study. First, for branch prediction, the DNNs outperform the perceptron model as high as 60-80%. Second, we analyze the impact of the depth of CNNs (i.e., number of convolutional layers and pooling layers) on the misprediction rates. The results confirm that deeper CNN structures can lead to lower misprediction rates. Third, the DBN could outperform our prior work, but not outperform the state-of-the-art TAGE-like branch predictor; the ResNet-50 could not only outperform our prior work, but also the Multi-poTAGE+SC and MTAGE+SC.

show abstract

A comparative analysis of pooling strategies for convolutional neural network based Hindi ASR

Cited by 22 publications

References 53 publications

A Comparison of Pooling Methods for Convolutional Neural Networks

A Comparison of Pooling Methods for Convolutional Neural Networks

Analysis of the Mel Scale Features Using Electrography and Speech Signals by Parameterized KNN and Xgboost

Exploring Convolution Neural Network for Branch Prediction

Contact Info

Product

Resources

About