Comparison of Several Acoustic Modeling Techniques for Speech Emotion Recognition

2016 ◽  
Vol 7 (1) ◽  
pp. 58-68 ◽  
Author(s):  
Imen Trabelsi ◽  
Med Salim Bouhlel
Keyword(s):  
Emotion Recognition ◽  
Linear Prediction ◽  
Recognition Rate ◽  
Gaussian Mixture ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Emotional States ◽  
Wide Range ◽  
Leibler Divergence ◽  
Perceptual Linear Prediction

Automatic Speech Emotion Recognition (SER) is a current research topic in the field of Human Computer Interaction (HCI) with a wide range of applications. The purpose of speech emotion recognition system is to automatically classify speaker's utterances into different emotional states such as disgust, boredom, sadness, neutral, and happiness. The speech samples in this paper are from the Berlin emotional database. Mel Frequency cepstrum coefficients (MFCC), Linear prediction coefficients (LPC), linear prediction cepstrum coefficients (LPCC), Perceptual Linear Prediction (PLP) and Relative Spectral Perceptual Linear Prediction (Rasta-PLP) features are used to characterize the emotional utterances using a combination between Gaussian mixture models (GMM) and Support Vector Machines (SVM) based on the Kullback-Leibler Divergence Kernel. In this study, the effect of feature type and its dimension are comparatively investigated. The best results are obtained with 12-coefficient MFCC. Utilizing the proposed features a recognition rate of 84% has been achieved which is close to the performance of humans on this database.

Comparison of Several Acoustic Modeling Techniques for Speech Emotion Recognition

2020 ◽  
pp. 283-293
Author(s):  
Imen Trabelsi ◽  
Med Salim Bouhlel
Keyword(s):  
Emotion Recognition ◽  
Linear Prediction ◽  
Recognition Rate ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Emotional States ◽  
Perceptual Linear Prediction

Automatic Speech Emotion Recognition (SER) is a current research topic in the field of Human Computer Interaction (HCI) with a wide range of applications. The purpose of speech emotion recognition system is to automatically classify speaker's utterances into different emotional states such as disgust, boredom, sadness, neutral, and happiness. The speech samples in this paper are from the Berlin emotional database. Mel Frequency cepstrum coefficients (MFCC), Linear prediction coefficients (LPC), linear prediction cepstrum coefficients (LPCC), Perceptual Linear Prediction (PLP) and Relative Spectral Perceptual Linear Prediction (Rasta-PLP) features are used to characterize the emotional utterances using a combination between Gaussian mixture models (GMM) and Support Vector Machines (SVM) based on the Kullback-Leibler Divergence Kernel. In this study, the effect of feature type and its dimension are comparatively investigated. The best results are obtained with 12-coefficient MFCC. Utilizing the proposed features a recognition rate of 84% has been achieved which is close to the performance of humans on this database.

Feature Selection for GUMI Kernel-Based SVM in Speech Emotion Recognition

2015 ◽  
Vol 6 (2) ◽  
pp. 57-68 ◽  
Author(s):  
Imen Trabelsi ◽  
Med Salim Bouhlel
Keyword(s):  
Emotion Recognition ◽  
Linear Prediction ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Bhattacharyya Distance ◽  
Human Machine Interaction ◽  
Speech Database ◽  
Perceptual Linear Prediction

Speech emotion recognition is the indispensable requirement for efficient human machine interaction. Most modern automatic speech emotion recognition systems use Gaussian mixture models (GMM) and Support Vector Machines (SVM). GMM are known for their performance and scalability in the spectral modeling while SVM are known for their discriminatory power. A GMM-supervector characterizes an emotional style by the GMM parameters (mean vectors, covariance matrices, and mixture weights). GMM-supervector SVM benefits from both GMM and SVM frameworks. In this paper, the GMM-UBM mean interval (GUMI) kernel based on the Bhattacharyya distance is successfully used. CFSSubsetEval combined with Best first algorithm and Greedy stepwise were also utilized on the supervectors space in order to select the most important features. This framework is illustrated using Mel-frequency cepstral (MFCC) coefficients and Perceptual Linear Prediction (PLP) features on two different emotional databases namely the Surrey Audio-Expressed Emotion and the Berlin Emotional speech Database.

Study of Speech Emotion Recognition Based on Prosodic Parameters and Facial Expression Features

2012 ◽  
Vol 241-244 ◽  
pp. 1677-1681
Author(s):  
Yu Tai Wang ◽  
Jie Han ◽  
Xiao Qing Jiang ◽  
Jing Zou ◽  
Hui Zhao
Keyword(s):  
Facial Expression ◽  
Emotion Recognition ◽  
Recognition Rate ◽  
Single Mode ◽  
Gaussian Mixture ◽  
Speech Emotion Recognition ◽  
Emotional States ◽  
Prosodic Features ◽  
Single Model ◽  
Model Recognition

The present status of speech emotion recognition was introduced in the paper. The emotional databases of Chinese speech and facial expressions were established with the noise stimulus and movies evoking subjects' emtion. For different emotional states, we analyzed the single-mode speech emotion recognitions based the prosodic features and the geometric features of facial expression. Then, we discussed the bimodal emotion recognition by the use of Gaussian Mixture Model. The experimental results show that, the bimodal emotion recognition rate combined with facial expression is about 6% higher than the single model recognition rate merely using prosodic features.

scholarly journals Multi-Layer Hybrid Fuzzy Classification Based on SVM and Improved PSO for Speech Emotion Recognition

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2891
Author(s):  
Shihan Huang ◽  
Hua Dang ◽  
Rongkun Jiang ◽  
Yue Hao ◽  
Chengbo Xue ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Emotion Recognition ◽  
Recognition Rate ◽  
Fuzzy Classification ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Fuzzy Support Vector Machine ◽  
Fuzzy C Means ◽  
Svm Model ◽  
Wide Range

Speech Emotion Recognition (SER) plays a significant role in the field of Human–Computer Interaction (HCI) with a wide range of applications. However, there are still some issues in practical application. One of the issues is the difference between emotional expression amongst various individuals, and another is that some indistinguishable emotions may reduce the stability of the SER system. In this paper, we propose a multi-layer hybrid fuzzy support vector machine (MLHF-SVM) model, which includes three layers: feature extraction layer, pre-classification layer, and classification layer. The MLHF-SVM model solves the above-mentioned issues by fuzzy c-means (FCM) based on identification information of human and multi-layer SVM classifiers, respectively. In addition, to overcome the weakness that FCM tends to fall into local minima, an improved natural exponential inertia weight particle swarm optimization (IEPSO) algorithm is proposed and integrated with fuzzy c-means for optimization. Moreover, in the feature extraction layer, non-personalized features and personalized features are combined to improve accuracy. In order to verify the effectiveness of the proposed model, all emotions in three popular datasets are used for simulation. The results show that this model can effectively improve the success rate of classification and the maximum value of a single emotion recognition rate is 97.67% on the EmoDB dataset.

Speech Emotion Recognition Using Multiple Discriminant Analysis and Gaussian Mixture Model

2013 ◽  
Vol 380-384 ◽  
pp. 3530-3533
Author(s):  
Yong Qiang Bao ◽  
Li Zhao ◽  
Cheng Wei Huang
Keyword(s):  
Discriminant Analysis ◽  
Emotion Recognition ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Speech Signal ◽  
Recognition Rate ◽  
Gaussian Mixture ◽  
Pitch Contour ◽  
Speech Emotion Recognition ◽  
Multiple Discriminant Analysis

In this paper we studied speech emotion recognition from Mandarin speech signal. Five basic emotion classes and the neutral state are considered. In a listening experiment we verified the speech corpus using a judgment matrix. Acoustic parameters including short-term energy, pitch contour, and formants are extracted from emotional speech signal. Gaussian mixture model is then adopted for training the emotion model. Due to the data challenge in GMM training, we use multiple discriminant analysis for feature optimization and compared with basic Fisher discriminant ratio based method. The experimental results show that using multiple discriminant analysis our GMM classifier gives a promising recognition rate for Mandarin speech emotion recognition.

Speech Emotion Feature Extraction Using FFT Spectrum Analysis

2015 ◽  
Vol 781 ◽  
pp. 551-554 ◽  
Author(s):  
Chaidiaw Thiangtham ◽  
Jakkree Srinonchat
Keyword(s):  
Feature Extraction ◽  
Emotion Recognition ◽  
Recognition Performance ◽  
Random Noise ◽  
Gaussian Mixture ◽  
Learning System ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Emotion Classification ◽  
Zero Crossing

Speech Emotion Recognition has widely researched and applied to some appllication such as for communication with robot, E-learning system and emergency call etc.Speech emotion feature extraction is an importance key to achieve the speech emotion recognition which can be classify for personal identity. Speech emotion features are extracted into several coefficients such as Linear Predictive Coefficients (LPCs), Linear Spectral Frequency (LSF), Zero-Crossing (ZC), Mel-Frequency Cepstrum Coefficients (MFCC) [1-6] etc. There are some of research works which have been done in the speech emotion recgnition. A study of zero-crossing with peak-amplitudes in speech emotion classification is introduced in [4]. The results shown that it provides the the technique to extract the emotion feature in time-domain, which still got the problem in amplitude shifting. The emotion recognition from speech is descrpited in [5]. It used the Gaussian Mixture Model (GMM) for extractor of feature speech. The GMM is provided the good results to reduce the back ground noise, howere it still have to focus on random noise in GMM for recognition model. The speech emotion recognition using hidden markov model and support vector machine is explained in [6]. The results shown the average performance of recognition system according to the features of speech emotion still has got the error information. Thus [1-6] provides the recognition performance which still requiers more focus on speech features.

scholarly journals On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1888
Author(s):  
Juraj Kacur ◽  
Boris Puterka ◽  
Jarmila Pavlovicova ◽  
Milos Oravec
Keyword(s):  
Emotion Recognition ◽  
Linear Prediction ◽  
Filter Banks ◽  
Vocal Tract ◽  
Statistical Tests ◽  
Extraction Methods ◽  
Speech Emotion Recognition ◽  
Speech Characteristics ◽  
Evaluation Phase ◽  
Cepstral Features

Many speech emotion recognition systems have been designed using different features and classification methods. Still, there is a lack of knowledge and reasoning regarding the underlying speech characteristics and processing, i.e., how basic characteristics, methods, and settings affect the accuracy, to what extent, etc. This study is to extend physical perspective on speech emotion recognition by analyzing basic speech characteristics and modeling methods, e.g., time characteristics (segmentation, window types, and classification regions—lengths and overlaps), frequency ranges, frequency scales, processing of whole speech (spectrograms), vocal tract (filter banks, linear prediction coefficient (LPC) modeling), and excitation (inverse LPC filtering) signals, magnitude and phase manipulations, cepstral features, etc. In the evaluation phase the state-of-the-art classification method and rigorous statistical tests were applied, namely N-fold cross validation, paired t-test, rank, and Pearson correlations. The results revealed several settings in a 75% accuracy range (seven emotions). The most successful methods were based on vocal tract features using psychoacoustic filter banks covering the 0–8 kHz frequency range. Well scoring are also spectrograms carrying vocal tract and excitation information. It was found that even basic processing like pre-emphasis, segmentation, magnitude modifications, etc., can dramatically affect the results. Most findings are robust by exhibiting strong correlations across tested databases.

scholarly journals A Research of Speech Emotion Recognition Based on Deep Belief Network and SVM

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Chenchen Huang ◽  
Wei Gong ◽  
Wenlong Fu ◽  
Dongyu Feng
Keyword(s):  
Feature Extraction ◽  
Emotion Recognition ◽  
Recognition Rate ◽  
Original Method ◽  
Speech Emotion Recognition ◽  
High Dimensional ◽  
Svm Classifier ◽  
Multiple Classifier System ◽  
Classifier System ◽  
Multiple Classifier

Feature extraction is a very important part in speech emotion recognition, and in allusion to feature extraction in speech emotion recognition problems, this paper proposed a new method of feature extraction, using DBNs in DNN to extract emotional features in speech signal automatically. By training a 5 layers depth DBNs, to extract speech emotion feature and incorporate multiple consecutive frames to form a high dimensional feature. The features after training in DBNs were the input of nonlinear SVM classifier, and finally speech emotion recognition multiple classifier system was achieved. The speech emotion recognition rate of the system reached 86.5%, which was 7% higher than the original method.

Speech Emotional Features Extraction Based on Electroglottograph

2013 ◽  
Vol 25 (12) ◽  
pp. 3294-3317 ◽  
Author(s):  
Lijiang Chen ◽  
Xia Mao ◽  
Pengfei Wei ◽  
Angelo Compare
Keyword(s):  
Emotion Recognition ◽  
Speech Signal ◽  
Vocal Tract ◽  
Vocal Folds ◽  
Distribution Coefficients ◽  
Speech Emotion Recognition ◽  
Support Vector ◽  
Power Law Distribution ◽  
Transform Coefficients ◽  
Better Than

This study proposes two classes of speech emotional features extracted from electroglottography (EGG) and speech signal. The power-law distribution coefficients (PLDC) of voiced segments duration, pitch rise duration, and pitch down duration are obtained to reflect the information of vocal folds excitation. The real discrete cosine transform coefficients of the normalized spectrum of EGG and speech signal are calculated to reflect the information of vocal tract modulation. Two experiments are carried out. One is of proposed features and traditional features based on sequential forward floating search and sequential backward floating search. The other is the comparative emotion recognition based on support vector machine. The results show that proposed features are better than those commonly used in the case of speaker-independent and content-independent speech emotion recognition.

A Mathematical Morphological Processing of Spectrograms for the Tone of Chinese Vowels Recognition

2014 ◽  
Vol 571-572 ◽  
pp. 665-671 ◽  
Author(s):  
Sen Xu ◽  
Xu Zhao ◽  
Cheng Hua Duan ◽  
Xiao Lin Cao ◽  
Hui Yan Li ◽  
...  
Keyword(s):  
Neural Networks ◽  
Speech Recognition ◽  
Emotion Recognition ◽  
Recognition Rate ◽  
Morphological Processing ◽  
Speech Emotion Recognition ◽  
Normal Tone ◽  
Tone Recognition ◽  
Tone Signal ◽  
The Neural Networks

As One of Features from other Languages, the Chinese Tone Changes of Chinese are Mainly Decided by its Vowels, so the Vowel Variation of Chinese Tone Becomes Important in Speech Recognition Research. the Normal Tone Recognition Ways are Always Based on Fundamental Frequency of Signal, which can Not Keep Integrity of Tone Signal. we Bring Forward to a Mathematical Morphological Processing of Spectrograms for the Tone of Chinese Vowels. Firstly, we will have Pretreatment to Recording Good Tone Signal by Using Cooledit Pro Software, and Converted into Spectrograms; Secondly, we will do Smooth and the Normalized Pretreatment to Spectrograms by Mathematical Morphological Processing; Finally, we get Whole Direction Angle Statistics of Tone Signal by Skeletonization way. the Neural Networks Stimulation Shows that the Speech Emotion Recognition Rate can Reach 92.50%.

Sign in / Sign up

Export Citation Format

Share Document