Wyniki wyszukiwania - Biblioteka Nauki

1

Speech emotion recognition under white noise

100%

Huang C. , Chen G. , Yu H. , Bao Y. , Zhao L.

Archives of Acoustics

|

2013

|

tom Vol. 38, No. 4

457--463

EN

Speaker‘s emotional states are recognized from speech signal with Additive white Gaussian noise (AWGN). The influence of white noise on a typical emotion recogniztion system is studied. The emotion classifier is implemented with Gaussian mixture model (GMM). A Chinese speech emotion database is used for training and testing, which includes nine emotion classes (e.g. happiness, sadness, anger, surprise, fear, anxiety, hesitation, confidence and neutral state). Two speech enhancement algorithms are introduced for improved emotion classification. In the experiments, the Gaussian mixture model is trained on the clean speech data, while tested under AWGN with various signal to noise ratios (SNRs). The emotion class model and the dimension space model are both adopted for the evaluation of the emotion recognition system. Regarding the emotion class model, the nine emotion classes are classified. Considering the dimension space model, the arousal dimension and the valence dimension are classified into positive regions or negative regions. The experimental results show that the speech enhancement algorithms constantly improve the performance of our emotion recognition system under various SNRs, and the positive emotions are more likely to be miss-classified as negative emotions under white noise environment.

2

Speech Emotion Recognition Based on Sparse Representation

100%

Yan J. , Wang X. , Gu W. , Ma L.

|

nr 4

3

Speech Emotion Recognition Using a Multi-Time-Scale Approach to Feature Aggregation and an Ensemble of SVM Classifiers

100%

Stefanowska A. , Zieliński S. K.

Archives of Acoustics

|

2024

|

tom Vol. 49, nr 2

153--168

EN

Due to its relevant real-life applications, the recognition of emotions from speech signals constitutes a popular research topic. In the traditional methods applied for speech emotion recognition, audio features are typically aggregated using a fixed-duration time window, potentially discarding information conveyed by speech at various signal durations. By contrast, in the proposed method, audio features are aggregated simultaneously using time windows of different lengths (a multi-time-scale approach), hence, potentially better utilizing information carried at phonemic, syllabic, and prosodic levels compared to the traditional approach. A genetic algorithm is employed to optimize the feature extraction procedure. The features aggregated at different time windows are subsequently classified by an ensemble of support vector machine (SVM) classifiers. To enhance the generalization property of the method, a data augmentation technique based on pitch shifting and time stretching is applied. According to the obtained results, the developed method outperforms the traditional one for the selected datasets, demonstrating the benefits of using a multi-time-scale approach to feature aggregation.

4

Speech emotion recognition based on sparse representation

100%

Yan J. , Wang X. , Gu W. , Ma L.

Archives of Acoustics

|

2013

|

tom Vol. 38, No. 4

465--470

EN

Speech emotion recognition is deemed to be a meaningful and intractable issue among a number of do- mains comprising sentiment analysis, computer science, pedagogy, and so on. In this study, we investigate speech emotion recognition based on sparse partial least squares regression (SPLSR) approach in depth. We make use of the sparse partial least squares regression method to implement the feature selection and dimensionality reduction on the whole acquired speech emotion features. By the means of exploiting the SPLSR method, the component parts of those redundant and meaningless speech emotion features are lessened to zero while those serviceable and informative speech emotion features are maintained and selected to the following classification step. A number of tests on Berlin database reveal that the recogni- tion rate of the SPLSR method can reach up to 79.23% and is superior to other compared dimensionality reduction methods.

5

Speech Emotion Recognition under White Noise

88%

Huang C. , Chen G. , Yu H. , Bao Y. , Zhao L.

|

nr 4

6

Speech emotion recognition system for social robots

75%

Juszkiewicz Ł.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2013

|

tom Vol. 7, No. 4

59--65

EN

The paper presents a speech emotion recognition system for social robots. Emotions are recognised using global acoustic features of the speech. The system implements the speech parameters calculation, features extraction, features selection and classification. All these phases are described. The system was verified using the two emotional speech databases: Polish and German. Perspectives for using such system in the social robots are presented.

7

Generalized Maximal Margin Discriminant Analysis for Speech Emotion Recognition

75%

Jin Y. , Zheng W. , Zhao L. , Yan J.

Przegląd Elektrotechniczny

|

2013

|

tom R. 89, nr 5

86-91

EN

A novel speech emotion recognition method based on the generalized maximum margin discriminant analysis (GMMDA) method is proposed in this paper. GMMDA is a multi-class extension of our proposed two-class dimensionality reduction method based on maximum margin discriminant analysis (MMDA), which utilizes the normal direction of optimal hyperplane of linear support vector machine (SVM) as the projection vector for feature extraction. To generate an optimal set of projection vectors from MMDA-based dimensionality reduction method, we impose orthogonal restrictions on the projection vectors and then recursively solve the problem. Moreover, to deal with the multi-class speech emotion recognition problem, we present two recognition schemes based on our proposed dimensionality reduction approach. One is using “one-versus-one" strategy for multi-class classification, and the other one is to compose the projection vectors of each pair of classes to obtain a transformation matrix for the multi-class dimensionality reduction.

PL

W artykule przedstawiono metodę analizy emisji głosu pod kątem rozpoznawania emocji. Rozwiązanie bazuje na analizie dyskryminacyjnej maksymalnego marginesu GMMDA.

8

Automatic speech based emotion recognition using paralinguistics features

75%

Hook J. , Noroozi F. , Toygar O. , Anbarjafari G.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2019

|

tom Vol. 67, nr 3

479--488

EN

Affective computing studies and develops systems capable of detecting humans affects. The search for universal well-performing features for speech-based emotion recognition is ongoing. In this paper, a?small set of features with support vector machines as the classifier is evaluated on Surrey Audio-Visual Expressed Emotion database, Berlin Database of Emotional Speech, Polish Emotional Speech database and Serbian emotional speech database. It is shown that a?set of 87 features can offer results on-par with state-of-the-art, yielding 80.21, 88.6, 75.42 and 93.41% average emotion recognition rate, respectively. In addition, an experiment is conducted to explore the significance of gender in emotion recognition using random forests. Two models, trained on the first and second database, respectively, and four speakers were used to determine the effects. It is seen that the feature set used in this work performs well for both male and female speakers, yielding approximately 27% average emotion recognition in both models. In addition, the emotions for female speakers were recognized 18% of the time in the first model and 29% in the second. A?similar effect is seen with male speakers: the first model yields 36%, the second 28% a?verage emotion recognition rate. This illustrates the relationship between the constitution of training data and emotion recognition accuracy.

9

Balancing Privacy and Accuracy in Federated Learning for Speech Emotion Recognition

63%

Mohammadi S. , Mohammadi M. , Sinaei S. , Balador A. , Nowroozi E. , Flammini F. , Conti M.

Annals of Computer Science and Information Systems

|

2023

|

tom Vol. 35

191--199

EN

Speech Emotion Recognition (SER) is a valuable technology that identifies human emotions from spoken language, enabling the development of context-aware and personalized intelligent systems. To protect user privacy, Federated Learning (FL) has been introduced, enabling local training of models on user devices. However, FL raises concerns about the potential exposure of sensitive information from local model parameters, which is especially critical in applications like SER that involve personal voice data. Local Differential Privacy (LDP) has been successful in preventing privacy leaks in image and video data. However, it encounters notable accuracy degradation when applied to speech data, especially in the presence of high noise levels. In this paper, we propose an approach called LDP-FL with CSS, which combines LDP with a novel client selection strategy (CSS). By leveraging CSS, we aim to improve the representatives of updates and mitigate the adverse effects of noise on SER accuracy while ensuring client privacy through LDP. Furthermore, we conducted model inversion attacks to evaluate the robustness of LDP-FL in preserving privacy. These attacks involved an adversary attempting to reconstruct individuals' voice samples using the output labels provided by the SER model. The evaluation results reveal that LDP-FL with CSS achieved an accuracy of 65-70\%, which is 4\% lower than the initial SER model accuracy. Furthermore, LDP-FL demonstrated exceptional resilience against model inversion attacks, outperforming the non-LDP method by a factor of 10. Overall, our analysis emphasizes the importance of achieving a balance between privacy and accuracy in accordance with the requirements of the SER application.

10

System rozpoznawania emocji wypowiedzi na potrzeby robotów społecznych

63%

Juszkiewicz Ł.

Prace Naukowe Politechniki Warszawskiej. Elektronika

|

2012

|

tom z. 182, t. 2

695--704

PL

W artykule przedstawiono realizację systemu rozpoznawania emocji wypowiedzi na podstawie intonacji głosu. Użyto paradygmatu opartego na globalnych statystykach wektorów cech. Omówione zostały poszczególne etapy procesu klasyfikacji: akwizycja sygnału mowy, jego parametryzacja, ekstrakcja cech, ich selekcja oraz klasyfikacja. Przeprowadzona została weryfikacja skuteczności systemu przy użyciu dwóch baz mowy emocjonalnej: polskiej oraz niemieckiej.

EN

The paper presents speech emotion recognition system for social robots. Emotions are recognized using global prosodic features of speech. System implements speech parameters calculation, features extraction, features selection and classification. All thees phases are described. System was verified using two emotional speech databases: Polish and English. Perspectives for using such system in social robots are presented.

11

Speech emotion recognition using wavelet packet reconstruction with attention-based deep recurrent neutral networks

51%

Meng H. , Yan T. , Wei H. , Ji X.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

tom Vol. 69, nr 1

art. no. e136300

EN

Speech emotion recognition (SER) is a complicated and challenging task in the human-computer interaction because it is difficult to find the best feature set to discriminate the emotional state entirely. We always used the FFT to handle the raw signal in the process of extracting the low-level description features, such as short-time energy, fundamental frequency, formant, MFCC (mel frequency cepstral coefficient) and so on. However, these features are built on the domain of frequency and ignore the information from temporal domain. In this paper, we propose a novel framework that utilizes multi-layers wavelet sequence set from wavelet packet reconstruction (WPR) and conventional feature set to constitute mixed feature set for achieving the emotional recognition with recurrent neural networks (RNN) based on the attention mechanism. In addition, the silent frames have a disadvantageous effect on SER, so we adopt voice activity detection of autocorrelation function to eliminate the emotional irrelevant frames. We show that the application of proposed algorithm significantly outperforms traditional features set in the prediction of spontaneous emotional states on the IEMOCAP corpus and EMODB database respectively, and we achieve better classification for both speaker-independent and speaker-dependent experiment. It is noteworthy that we acquire 62.52% and 77.57% accuracy results with speaker-independent (SI) performance, 66.90% and 82.26% accuracy results with speaker-dependent (SD) experiment in final.