• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2439-2442
• /
• 2003

In this paper, we examine the acoustic characteristics of Korean vowels on pitch alteration utterance. The prosody is known as an indicator of acoustic characteristics of emotions. Also, speech is acoustically differenced according to the emotional variation and environmental variation, although speaker utters the same speech. We analyzed the spectral envelopes and formants from the voiced regions as data points on the speech waveform.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.377-380
• /
• 2002

In this paper, speaker and context independent emotion recognition using speech signal is studied. For this purpose, a corpus of emotional speech data recorded and classified according to the emotion using the subjective evaluation were used to make statical feature vectors such as average, standard deviation and maximum value of pitch and energy and to evaluate the performance of the conventional pattern matching algorithms. The vector quantization based emotion recognition system is proposed for speaker and context independent emotion recognition. Experimental results showed that vector quantization based emotion recognizer using MFCC parameters showed better performance than that using the Pitch and energy Parameters.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.67-70
• /
• 2007

The present paper focuses on the interaction between lexical-semantic information and affective prosody. The previous studies showed that the influence of lexical-semantic information on the affective evaluation of the prosody was relatively clear, but the influence of emotional prosody on the word evaluation remains still ambiguous. In the present, we explore whether affective prosody influence on the evaluation of affective meaning of a word and vice versa, using more ecological stimulus (sentences) than simple words. We asked participants to evaluate the emotional valence of the sentences which were recorded with affective prosody (negative, neutral, and positive) in Experiment 1 and the emotional valence of their prosodies in Experiment 2. The results showed that the emotional valence of prosody can influence on the emotional evaluation of sentences and vice versa. Interestingly, the positive prosody is likely to be more responsible to this interaction.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.2
• /
• pp.150-154
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition are determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section.

• Journal of Korea Multimedia Society
• /
• v.10 no.11
• /
• pp.1530-1537
• /
• 2007

In this paper, we implemented a speech emotion recognition system that can distinguish human emotional states from recorded speech captured by a single microphone and classify them into four categories: neutrality, happiness, sadness and anger. In general, a speech recorded with a microphone contains background noises due to the speaker environment and the microphone characteristic, which can result in serious system performance degradation. In order to minimize the effect of these noises and to improve the system performance, a MA(Moving Average) filter with a relatively simple structure and low computational complexity was adopted. Then a SFS(Sequential Forward Selection) feature optimization method was implemented to further improve and stabilize the system performance. For speech emotion classification, a SVM pattern classifier is used. The experimental results indicate the emotional classification performance around 65% in the computer simulation and 62% on the ARM platform.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.462-475
• /
• 2022

Although researchers have proposed numerous techniques for speech emotion recognition, its performance remains unsatisfactory in many application scenarios. In this study, we propose a speech emotion recognition model based on a genetic algorithm (GA)-decision tree (DT) fusion of deep and acoustic features. To more comprehensively express speech emotional information, first, frame-level deep and acoustic features are extracted from a speech signal. Next, five kinds of statistic variables of these features are calculated to obtain utterance-level features. The Fisher feature selection criterion is employed to select high-performance features, removing redundant information. In the feature fusion stage, the GA is is used to adaptively search for the best feature fusion weight. Finally, using the fused feature, the proposed speech emotion recognition model based on a DT support vector machine model is realized. Experimental results on the Berlin speech emotion database and the Chinese emotion speech database indicate that the proposed model outperforms an average weight fusion method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.3
• /
• pp.284-288
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.347-350
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition is determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section. Truly, emotion recognition technique is not mature. That is, the emotion feature selection, relevant classification method selection, all these problems are disputable. So, we wish this paper to be a reference for the disputes.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• Phonetics and Speech Sciences
• /
• v.9 no.3
• /
• pp.41-47
• /
• 2017

The purpose of this study is to examine how speakers use VOT and f0 to distinguish tense, lax, and aspirated stops in isolated sentence reading and paragraph readings. To do so, a total of 20 males between the ages of 20-25 years old were asked to read (1) isolated sentences, (2) information-oriented text and (3) emotional expressive texts in which the stop pronunciation's VOT value and f0 were measured thereafter. The main results are as follows. In the isolate sentence reading, lax stops, and aspirated stops were distinguished by both VOT and f0, but for the Korean men that read reading texts, VOT is not a cue to distinguish between lax and aspirated stops. In general, the VOT differences between lax stops and aspirated stops were smaller for information-oriented texts and emotional expressive texts than that of the isolate sentence reading. In the paragraph reading that induces a natural utterance, the f0 dependence is greater for the distinction between lax and aspirated stops.