Emotion Recognition From Speech Using Wavelet Packet Transform Cochlear Filter Bank and Random Forest Classifier

Hamsa, Shibani; Shahin, Ismail; Iraqi, Youssef; Werghi, Naoufel

doi:10.1109/access.2020.2991811

Cited by 38 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Te calculation process for the reset gate is shown in equation ( 6), while the calculation of GRU output is shown in equation (8). Te key distinction between vanilla RNNs and GRUs is that the latter supports gating of the hidden state.…”

Section: Gated Recurrentmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Methods for Arabic Autoencoder Speech Recognition System for Electro-Larynx Device

Ameen

Kadhim

2023

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

Recent advances in speech recognition have achieved remarkable performance comparable with human transcribers’ abilities. But this significant performance is not the same for all the spoken languages. The Arabic language is one of them. Arabic speech recognition is bounded to the lack of suitable datasets. Artificial intelligence algorithms have shown promising capabilities for Arabic speech recognition. Arabic is the official language of 22 countries, and it has been estimated that 400 million people speak the Arabic language worldwide. Speech disabilities have been one of the expanding problems in the last decades, even in kids. Some devices can be used to generate speech for those people. One of these devices is the Servox Digital Electro-Larynx (EL). In this research, we developed an autoencoder with a combination of long short-term memory (LSTM) and gated recurrent units (GRU) models to recognize recorded signals from Servox Digital EL Electro-Larynx. The proposed framework consisted of three steps: denoising, feature extraction, and Arabic speech recognition. The experimental results show 95.31% accuracy for Arabic speech recognition with the proposed model. In this research, we evaluated different combinations of LSTM and GRU for constructing the best autoencoder. A rigorous evaluation process indicates better performance with the use of GRU in both encoder and decoder structures. The proposed model achieved a 4.69% word error rate (WER). Experimental results confirm that the proposed model can be used for developing a real-time app to recognize common Arabic spoken words.

show abstract

Section: Gated Recurrentmentioning

confidence: 99%

“…But situations for recording sounds might be stressful, or the collected dataset may contain noise. Hamsa et al [8] proposed a method for Arabic emotion recognition in stressful and noisy situations. Tey proposed a model based on novel wavelet packet transform as denoising techniques and a random forest model for emotion recognition.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Methods for Arabic Autoencoder Speech Recognition System for Electro-Larynx Device

Ameen

Kadhim

2023

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

show abstract

“…After normalizing the CNN features, temporal information is learned by moving the components to the deep bi-directional long-term memory (BiLSTM). Hamsa et al [21] proposed a noise and interference-resilient SER system. The speaker's emotion is examined by considering the energy, spectral, and time parameters.…”

Section: Literature Surveymentioning

confidence: 99%

Multi-Attribute Feature Extraction and Selection for Emotion Recognition from Speech through Machine Learning

Ramyasree¹,

Kumar²

2023

View full text Add to dashboard Cite

Speech-based emotion recognition is still challenging due to its complexity despite being widely used in applications relating to emotions. In this paper, we developed a framework by considering three features: Prosodic features, Wavelet, and Spectral features. Under Prosodic, pitch and energy are considered, while under wavelet features, the approximation and detailed sub-bands ate fur scales are considered. Mel-Frequency Cepstral Coefficients (MFCC), Formants, and Long-Term Average Spectrum (LTAS) are all measured from speech signals as part of spectral features. Further, the significant features are selected based on nonlinear statistics, and dimensionality reduction is accomplished through Fisher Criterion. Spearman Rank Correlation is employed to find the nonlinear statistics under correlation analysis. For categorization, a Support Vector Machine and Decision Tree are used. The proposed method is simulated over RAVDESS, SAVEE, EMOVO, and URDU databases, and the observed recognition rates are approximately 79.66%, 88.99%, 87.68%, and 95.78%, respectively.

show abstract

“…The prediction value is constructed from individual decision trees by using different aggregation policies [15] like majority voting, computing mean, or median, depending on the problem type. Due to its simplicity and efficiency, the Random Forest model has been successfully applied to several practical problems like patient health prediction [2], image classification [3], emotion recognition [4], malware detection [5], [16] and user response prediction [7], [17].…”

Section: Related Workmentioning

confidence: 99%

Topological Forest

Bayır

Shamsi

Kaynak³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

We propose a new ML model called Topological Forest that contains an ensemble of decision trees. Unlike a vanilla Random Forest, Topological Forest has a special training process that selects a smaller number of decision trees on a topological graph representation that TDA Mapper constructs. Compared to Vanilla Random Forest, Topological Forest significantly improves the computational efficiency of inference time due to the smaller ensemble size and selection of better decision trees while keeping the diversity of decision trees. Our experiments show that Topological Forest can speed up inference time by more than 100x on average while compromising at most 2% reduction in the AUC metric for the prediction quality.

show abstract

Emotion Recognition From Speech Using Wavelet Packet Transform Cochlear Filter Bank and Random Forest Classifier

Cited by 38 publications

References 29 publications

Deep Learning Methods for Arabic Autoencoder Speech Recognition System for Electro-Larynx Device

Deep Learning Methods for Arabic Autoencoder Speech Recognition System for Electro-Larynx Device

Multi-Attribute Feature Extraction and Selection for Emotion Recognition from Speech through Machine Learning

Topological Forest

Contact Info

Product

Resources

About