Can I read An Ensemble 1D-CNN-LSTM-GRU Model with Data Augmentation for Speech Emotion Recognition on EtoBox?

An Ensemble 1D-CNN-LSTM-GRU Model with Data Augmentation for Speech Emotion Recognition by Ahmed, Md. Rayhan; Islam, Salekul; D, Ph.; Islam, A. K. M. Muzahidul; D, Ph.; Shatabda, Swakkhar; D, Ph. is a scholarly article available to read on EtoBox.

What is An Ensemble 1D-CNN-LSTM-GRU Model with Data Augmentation for Speech Emotion Recognition about?

In this paper, we propose an ensemble of deep neural networks along with data augmentation (DA) learned using effective speech-based features to recognize emotions from speech. Our ensemble model is built on three deep neural network-based models. These neural networks are built using the basic local feature acquiring blocks (LFAB) which are consecutive layers of dilated 1D Convolutional Neural networks followed by the max pooling and batch normalization layers. To acquire the long-term dependencies in speech signals further two variants are proposed by adding Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM) layers respectively. All three network models have consecutive fully connected layers before the final softmax layer for classification. The ensemble model uses a weighted average to provide the final classification. We have utilized five standard benchmark datasets: TESS, EMO-DB, RAVDESS, SAVEE, and CREMA-D for evaluation. We have performed DA by injecting Additive White Gaussian Noise, pitch shifting, and stretching the signal level to generalize the models, and thus increasing the accuracy of the models and reducing the overfitting as well. We handcrafted five ca

Author

Ahmed, Md. Rayhan; Islam, Salekul; D, Ph.; Islam, A. K. M. Muzahidul; D, Ph.; Shatabda, Swakkhar; D, Ph.

Published

2021

Language

EN