METHODS FOR EXTRACTION OF ACOUSTIC CHARACTERISTICS IN THE SPEECH RECOGNITION PROBLEM BY RECURRENT NEURAL NETWORKS WITH LONG SHORT-TERM MEMORY

Short Term Memory ◽

Audio Signal ◽

Acoustic Features ◽

Short Term ◽

Acoustic Characteristics ◽

Term Memory ◽

The paper presents some methods for extracting features from an audio signal, the problem of recognizing Russian speech using a recurrent neural network LSTM are solved, the results of recognition for different acoustic features are analyzed.

Automatic Classification of Indian Languages into Tonal and Non-tonal Categories Using Cascade Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) Recurrent Neural Networks

2018 International Conference on Signal Processing and Communications (SPCOM) ◽

10.1109/spcom.2018.8724471 ◽

2018 ◽

Author(s):

Chuya China ◽

Dipjyoti Bisharad ◽

Rabul Hussain Laskar

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Short Term Memory ◽

Indian Languages ◽

Short Term ◽

Term Memory ◽

Cascade convolutional neural network‐long short‐term memory recurrent neural networks for automatic tonal and nontonal preclassification‐based Indian language identification

Expert Systems ◽

10.1111/exsy.12544 ◽

2020 ◽

Vol 37 (5) ◽

Author(s):

Chuya China Bhanja ◽

Mohammad A. Laskar ◽

Rabul H. Laskar

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Short Term Memory ◽

Language Identification ◽

Short Term ◽

Indian Language ◽

Term Memory ◽

Structured Sparsification of Gated Recurrent Neural Networks

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5938 ◽

2020 ◽

Vol 34 (04) ◽

pp. 4989-4996

Author(s):

Ekaterina Lobacheva ◽

Nadezhda Chirkova ◽

Alexander Markovich ◽

Dmitry Vetrov

Keyword(s):

Neural Network ◽

Neural Networks ◽

Text Classification ◽

Short Term Memory ◽

Language Modeling ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Network Compression

One of the most popular approaches for neural network compression is sparsification — learning sparse weight matrices. In structured sparsification, weights are set to zero by groups corresponding to structure units, e. g. neurons. We further develop the structured sparsification approach for the gated recurrent neural networks, e. g. Long Short-Term Memory (LSTM). Specifically, in addition to the sparsification of individual weights and neurons, we propose sparsifying the preactivations of gates. This makes some gates constant and simplifies an LSTM structure. We test our approach on the text classification and language modeling tasks. Our method improves the neuron-wise compression of the model in most of the tasks. We also observe that the resulting structure of gate sparsity depends on the task and connect the learned structures to the specifics of the particular tasks.

Perbandingan Model Deep Learning untuk Klasifikasi Sentiment Analysis dengan Teknik Natural Languange Processing

Jurnal Teknologi dan Manajemen Informatika ◽

10.26905/jtmi.v7i2.6506 ◽

2021 ◽

Vol 7 (2) ◽

pp. 113-121

Author(s):

Firman Pradana Rachman

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Sentiment Analysis ◽

Short Term Memory ◽

Short Term ◽

Term Memory ◽

Setiap orang mempunyai pendapat atau opini terhadap suatu produk, tokoh masyarakat, atau pun sebuah kebijakan pemerintah yang tersebar di media sosial. Pengolahan data opini itu di sebut dengan sentiment analysis. Dalam pengolahan data opini yang besar tersebut tidak hanya cukup menggunakan machine learning, namun bisa juga menggunakan deep learning yang di kombinasikan dengan teknik NLP (Natural Languange Processing). Penelitian ini membandingkan beberapa model deep learning seperti CNN (Convolutional Neural Network), RNN (Recurrent Neural Networks), LSTM (Long Short-Term Memory) dan beberapa variannya untuk mengolah data sentiment analysis dari review produk amazon dan yelp.

RECURRENT NEURAL NETWORKS FOR MUSICAL PITCH MEMORY AND CLASSIFICATION

International Journal of Artificial Intelligence Tools ◽

10.1142/s0218213005002120 ◽

2005 ◽

Vol 14 (01n02) ◽

pp. 329-342 ◽

Cited By ~ 2

Author(s):

JUDY A. FRANKLIN ◽

KRYSTAL K. LOCKE

Keyword(s):

Neural Network ◽

Neural Networks ◽

Recurrent Neural Network ◽

Short Term Memory ◽

Recurrent Networks ◽

Short Term ◽

Term Memory ◽

Musical Pitch ◽

We present results from experiments in using several pitch representations for jazz-oriented musical tasks performed by a recurrent neural network. We have run experiments with several kinds of recurrent networks for this purpose, and have found that Long Short-term Memory networks provide the best results. We show that a new pitch representation called Circles of Thirds works as well as two other published representations for these tasks, yet it is more succinct and enables faster learning. We then discuss limited results using other types of networks on the same tasks.