Convolutional Neural Network (CNN) Based Speech-Emotion Recognition

Qayyum, Alif Bin Abdul; Arefeen, Asiful; Shahnaz, Celia

doi:10.1109/spicscon48833.2019.9065172

Cited by 39 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Precision is the ability of our model to check the correctly predicted positives from all the predicted positives and is given by Eq. (5). Our model has the highest precision of 95% for surprise emotion and lowest for happy emotion with precision of 82%.…”

Section: Resultsmentioning

confidence: 77%

See 1 more Smart Citation

Speech Emotion Recognition using Time Distributed CNN and LSTM

et al. 2021

View full text Add to dashboard Cite

Speech has several distinguishing characteristic features which has remained a state-of-the-art tool for extracting valuable information from audio samples. Our aim is to develop a emotion recognition system using these speech features, which would be able to accurately and efficiently recognize emotions through audio analysis. In this article, we have employed a hybrid neural network comprising four blocks of time distributed convolutional layers followed by a layer of Long Short Term Memory to achieve the same.The audio samples for the speech dataset are collectively assembled from RAVDESS, TESS and SAVEE audio datasets and are further augmented by injecting noise. Mel Spectrograms are computed from audio samples and are used to train the neural network. We have been able to achieve a testing accuracy of about 89.26%.

show abstract

Section: Resultsmentioning

confidence: 77%

“…T ruePositive T ruePositive + FalsePositive (5) Recall measures the model ability to check the correct positive from all the existing positives in the test dataset and is given by Eq. (6).…”

Section: Precision =mentioning

confidence: 99%

Speech Emotion Recognition using Time Distributed CNN and LSTM

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Over the last few years, researchers have introduced different deep learning algorithms using various discriminative features [18][19][20]. At present, deep learning methods still use several low-level descriptor (LLD) features, which are different from traditional SER features [21]. So, extracting more detailed and relevant emotional information from speech is the first issue we have to address.…”

Section: Introductionmentioning

confidence: 99%

Advanced Fusion-Based Speech Emotion Recognition System Using a Dual-Attention Mechanism with Conv-Caps and Bi-GRU Features

Maji¹,

Swain²,

Mustaqeem

2022

Electronics

View full text Add to dashboard Cite

Recognizing the speaker’s emotional state from speech signals plays a very crucial role in human–computer interaction (HCI). Nowadays, numerous linguistic resources are available, but most of them contain samples of a discrete length. In this article, we address the leading challenge in Speech Emotion Recognition (SER), which is how to extract the essential emotional features from utterances of a variable length. To obtain better emotional information from the speech signals and increase the diversity of the information, we present an advanced fusion-based dual-channel self-attention mechanism using convolutional capsule (Conv-Cap) and bi-directional gated recurrent unit (Bi-GRU) networks. We extracted six spectral features (Mel-spectrograms, Mel-frequency cepstral coefficients, chromagrams, the contrast, the zero-crossing rate, and the root mean square). The Conv-Cap module was used to obtain Mel-spectrograms, while the Bi-GRU was used to obtain the rest of the spectral features from the input tensor. The self-attention layer was employed in each module to selectively focus on optimal cues and determine the attention weight to yield high-level features. Finally, we utilized a confidence-based fusion method to fuse all high-level features and pass them through the fully connected layers to classify the emotional states. The proposed model was evaluated on the Berlin (EMO-DB), Interactive Emotional Dyadic Motion Capture (IEMOCAP), and Odia (SITB-OSED) datasets to improve the recognition rate. During experiments, we found that our proposed model achieved high weighted accuracy (WA) and unweighted accuracy (UA) values, i.e., 90.31% and 87.61%, 76.84% and 70.34%, and 87.52% and 86.19%, respectively, demonstrating that the proposed model outperformed the state-of-the-art models using the same datasets.

show abstract

“…Some of them are convolutional neural network (CNN), recurrent neural network (RNN), and support vector machine (SVM) [10], [14], [17] among those classification models, CNN is confident in processing pictures and applying them to speech emotion recognition since the extracted audio features form can be a picture. Prior research of speech emotion recognition shows that CNN produces higher accuracy than RNN and SVM models [14], [18]. This condition allows us to choose CNN as the platform for the speech emotion recognition model.…”

mentioning

confidence: 99%

“…Most speech emotion recognition research uses datasets equipped with emotion labels. Some of the datasets used by researchers are Ryerson audio-visual database of emotional speech and song (RAVDESS), surrey audio-visual expressed emotion (SAVEE), The interactive emotional dyadic motion capture (IEMOCAP), Toronto emotional speech set (TESS), CASIA, dan EMO [9], [11], [14], [15], [22], [23]. The work to combine datasets is expanded by de Pinto et al [15] to gain a model with better performance.…”

mentioning

confidence: 99%

Speech emotion recognition using 2D-convolutional neural network

Reggiswarashari

Sihwi

2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">This research proposes a speech emotion recognition model to predict human emotions using the convolutional neural network (CNN) by learning segmented audio of specific emotions. Speech emotion recognition utilizes the extracted features of audio waves to learn speech emotion characteristics; one of them is mel frequency cepstral coefficient (MFCC). Dataset takes a vital role to obtain valuable results in model learning. Hence this research provides the leverage of dataset combination implementation. The model learns a combined dataset with audio segmentation and zero padding using 2D-CNN. Audio segmentation and zero padding equalize the extracted audio features to learn the characteristics. The model results in 83.69% accuracy to predict seven emotions: neutral, happy, sad, angry, fear, disgust, and surprise from the combined dataset with the segmentation of the audio files.</span>

show abstract

Convolutional Neural Network (CNN) Based Speech-Emotion Recognition

Cited by 39 publications

References 8 publications

Speech Emotion Recognition using Time Distributed CNN and LSTM

Speech Emotion Recognition using Time Distributed CNN and LSTM

Advanced Fusion-Based Speech Emotion Recognition System Using a Dual-Attention Mechanism with Conv-Caps and Bi-GRU Features

Speech emotion recognition using 2D-convolutional neural network

Contact Info

Product

Resources

About