A Hybrid Emotion Recognition on Android Smart Phones

Zhang, Weishan; Meng, Xiangda; Lu, Qinghua; Rao, Yuan; Zhou, Jiehan

doi:10.1109/greencom-ithings-cpscom.2013.228

Cited by 6 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we will test this approach with larger speech datasets. In addition, lexical features contain large amounts of information that can be potentially used [ 28 ]. If we can make use of lexical features combined with speech features, the performance of speech emotion recognition should be improved.…”

Section: Discussionmentioning

confidence: 99%

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN

Zhu

Chen

Zhao

et al. 2017

Sensors

Self Cite

111

View full text Add to dashboard Cite

Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed.

show abstract

Section: Discussionmentioning

confidence: 99%

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN

Zhu

Chen

Zhao

et al. 2017

Sensors

Self Cite

111

View full text Add to dashboard Cite

show abstract

“…Furthermore, the data set is Computational Intelligence and Neuroscience not age or gender agnostic. We can improve the algorithms with more accurate and varied data sets [67] in the future to be used in everyday life by the broader public.…”

Section: Savee Data Setmentioning

confidence: 99%

Human-Computer Interaction with Detection of Speaker Emotions Using Convolution Neural Networks

Alnuaim

Zakariah

Alhadlaq

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Emotions play an essential role in human relationships, and many real-time applications rely on interpreting the speaker’s emotion from their words. Speech emotion recognition (SER) modules aid human-computer interface (HCI) applications, but they are challenging to implement because of the lack of balanced data for training and clarity about which features are sufficient for categorization. This research discusses the impact of the classification approach, identifying the most appropriate combination of features and data augmentation on speech emotion detection accuracy. Selection of the correct combination of handcrafted features with the classifier plays an integral part in reducing computation complexity. The suggested classification model, a 1D convolutional neural network (1D CNN), outperforms traditional machine learning approaches in classification. Unlike most earlier studies, which examined emotions primarily through a single language lens, our analysis looks at numerous language data sets. With the most discriminating features and data augmentation, our technique achieves 97.09%, 96.44%, and 83.33% accuracy for the BAVED, ANAD, and SAVEE data sets, respectively.

show abstract

“…Other researchers continue to conduct study using the soft biometric elements available to each individual using the elements such as mole, iris or eye retina [8], scar effect / tattoo [9], body figure [9], gender [10,11], [12], ethnicity [13], eye color, height [12], weight, hair color [14], age, BMI, walking style [15], sitting style [16], eyebrow, blood type [17], heartbeat, talking style [18], vein image [19], facial shape [20], facial skin / figure, and ear shape [17]. The results of previous studies have found that these elements can be used to identify individual users.…”

Section: Introductionmentioning

confidence: 99%

Identification of the Exclusivity of Individual’s Typing Style Using Soft Biometric Elements

Yaacob¹,

Idrus²,

Mustafa³

et al. 2021

AETiC

View full text Add to dashboard Cite

Biometric is used as a main security fence in a computer system. The unique characteristics of a person can be distinguished from each other. Human’s biometrics can be categorized into three types: morphological, biological and behavioural. Morphological biometrics uses physical features for recognition. Biological biometrics used to identify user based on biological features. Behavioural biometrics such as gender, culture, height and weight can be used as an additional security measure within a system. These biometric behavioural features are also known as soft biometric. This study uses soft biometric elements (gender, culture, region of birth and educational level) in the keystroke dynamic study to distinguish typing patterns in each of these categories. The Support Vector Machine (SVM) classification method is used to perform this classification for soft biometric identification. The results of this study have shown that soft biometrics in keystroke dynamic can be used to distinguish group of individuals typing.

show abstract

A Hybrid Emotion Recognition on Android Smart Phones

Cited by 6 publications

References 15 publications

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN

Human-Computer Interaction with Detection of Speaker Emotions Using Convolution Neural Networks

Identification of the Exclusivity of Individual’s Typing Style Using Soft Biometric Elements

Contact Info

Product

Resources

About