Speech Emotion Recognition UsingConvolutional Neural Network and Long-Short TermMemory

Dangol, Ranjana; Alsadoon, Abeer; Prasad, P. W. C.; Seher, Indra; Alsadoon, Omar Hisham

doi:10.1007/s11042-020-09693-w

Cited by 38 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The attention mechanism can better extract the emotional information of speech and remove the interference, which can improve the accuracy of the model. Ranjana Dangol et al [7] proposed an emotion recognition system combining CNN and LSTM with a relationship awareness self-attention mechanism. The average recognition accuracy of this system can reach 81.05%.…”

Section: Related Workmentioning

confidence: 99%

“…The input gate i t is determined by the current input data x t and the previous time unit output h t−1 , as in Equation ( 6). The forgetting gate f t controls the transmission of historical information, as per Equation (7). The output gate O t calculates the output value h t of the LSTM unit, as per Equation (8).…”

Section: 𝑐̃= 𝑡𝑎𝑛ℎ(𝑊mentioning

confidence: 99%

“…The machine-learning method has attracted great attention from researchers. Convolutional Neural Networks (CNNs) [3,5,6] and LSTM networks [7] and their combination [7][8][9] have been widely used. Misbah Farooq et al [8] used a feature-selection algorithm based on CNN to reduce the influence of artificial design that was insufficient to accurately describe the emotional state of the speaker.…”

Section: Introductionmentioning

confidence: 99%

“…In view of this, Yawei Mu et al [10] introduced Attention mechanism to establish CNN+BiLSTM+attention model and conducted experiments on the IEMOCAP data set, reaching the accuracy of 64.08%. Ranjana Dangol et al [7] established…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Impact of Attention Mechanisms on Speech Emotion Recognition

Chen

Zhang

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

Speech emotion recognition (SER) plays an important role in real-time applications of human-machine interaction. The Attention Mechanism is widely used to improve the performance of SER. However, the applicable rules of attention mechanism are not deeply discussed. This paper discussed the difference between Global-Attention and Self-Attention and explored their applicable rules to SER classification construction. The experimental results show that the Global-Attention can improve the accuracy of the sequential model, while the Self-Attention can improve the accuracy of the parallel model when conducting the model with the CNN and the LSTM. With this knowledge, a classifier (CNN-LSTM×2+Global-Attention model) for SER is proposed. The experiments result show that it could achieve an accuracy of 85.427% on the EMO-DB dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: 𝑐̃= 𝑡𝑎𝑛ℎ(𝑊mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Impact of Attention Mechanisms on Speech Emotion Recognition

Chen

Zhang

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Emotions are fundamental in the daily life of human beings as they play an essential role in human cognition, namely, in perception, rational decision-making, human interaction, and human intelligence [ 1 ]. With the development of artificial intelligence technology and deep learning, emotion recognition has broad prospects in human-computer interaction and clinical treatment, which has been widely concerned by researchers [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition Based on EEG Using Generative Adversarial Nets and Convolutional Neural Network

Pan

Wei

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Emotion recognition plays an important role in the field of human-computer interaction (HCI). Automatic emotion recognition based on EEG is an important topic in brain-computer interface (BCI) applications. Currently, deep learning has been widely used in the field of EEG emotion recognition and has achieved remarkable results. However, due to the cost of data collection, most EEG datasets have only a small amount of EEG data, and the sample categories are unbalanced in these datasets. These problems will make it difficult for the deep learning model to predict the emotional state. In this paper, we propose a new sample generation method using generative adversarial networks to solve the problem of EEG sample shortage and sample category imbalance. In experiments, we explore the performance of emotion recognition with the frequency band correlation and frequency band separation computational models before and after data augmentation on standard EEG-based emotion datasets. Our experimental results show that the method of generative adversarial networks for data augmentation can effectively improve the performance of emotion recognition based on the deep learning model. And we find that the frequency band correlation deep learning model is more conducive to emotion recognition.

show abstract

Cat swarm optimized ensemble technique for emotion recognition in speech signals

Butta¹,

Maddu²,

Sumalatha

2022

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARY One of the fastest and the natural mode of communication between humans is speech. Recently in speech signal processing, noncontact clinical issue, patient remote monitoring, and man–machine interaction application; emotion recognition from the speech is becoming a popular topic of research. The basic principle behind speech emotion recognition is to analyze the diverse emotions expressed by a speaker while uttering the same obsession under dissimilar emotional circumstances. A novel speech emotion recognition method is formulated in this research study in two major phases: spectral feature extraction and recognition. Initially, the extracted spectral skewness, delta AMS, spectral flux, spectral kurtosis, spectral spread, and spectral slope features from the input speech signal are subjected to the proposed ensemble classifier to determine the corresponding emotions from the input signal. The suggested ensemble classifier includes neural network 1, neural network 2, neural network 3, random forest, and recurrent neural network. The final recognized outcome is acquired from the RNN, which is enhanced via tuning its weight. A new improved cat‐swarm optimization algorithm is used to address this optimization problem. Finally, the obtained findings are compared to other state‐of‐the‐art algorithms.

show abstract

Speech Emotion Recognition UsingConvolutional Neural Network and Long-Short TermMemory

Cited by 38 publications

References 16 publications

The Impact of Attention Mechanisms on Speech Emotion Recognition

The Impact of Attention Mechanisms on Speech Emotion Recognition

Emotion Recognition Based on EEG Using Generative Adversarial Nets and Convolutional Neural Network

Cat swarm optimized ensemble technique for emotion recognition in speech signals

Contact Info

Product

Resources

About