Automated Speech Emotion Recognition on Smart Phones

Alshamsi, Humaid; Këpuska, Veton; Alshamsi, Hazza; Meng, Hongying

doi:10.1109/uemcon.2018.8796594

Cited by 8 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The short term power spectrum of sound is described by Mel-Frequency Cepstrum (MFC) [4], on the basis of a linear cosine transform to log power spectrum with a nonlinear Mel scale of frequency. By converting the conventional frequency to Mel Scale, MFCC [11] accounts for human perception for sensitivity at acceptable frequencies. MFC is easy to implement and hence has become a widely used method for speech recognition.…”

Section: Feature Extractionmentioning

confidence: 99%

“…The most popular approaches for classifications include Bayesian learning [6], the Linear Discriminant Analysis (LDA), the Support Vector Machine (SVM) [1,3] which is used as an extension of LDA with a high-dimensional feature space, the multi-layer Neural Network (NN) [14], and the Hidden Markov model (HMM) which captures temporal state transitions. The intensity of emotion [3] fluctuates on a voice from a low to a high level of emotion.. Hossain et al [9] used Cepstral Coefficient (CC) as voice feature and a fixed valued k-means clustered method for feature classification where value of k is determined by the number of emotional events that are evaluated in human physiology.SVM [7,8,11] is the most widely used classifier due to its efficiency in classifying high dimensional data where the number of features is greater than number of observations. SVMs have a major benefit over Artificial Neural Network(ANN) that, unlike ANNs, the solution to an SVM is global and exclusive.…”

Section: Classificationmentioning

confidence: 99%

“…The training of the proposed model is employed using RAVDESS [2,11] (Ryerson Audio-Visual Database of Emotional Speech and Song) dataset. The database of size 24.8 GB contains a total of 7356 files consisting of voice samples of 24 professional actors ,12 female and 12 male, vocalizing 2 lexically-matched statements.…”

Section: Data Selectionmentioning

confidence: 99%

“…The classification model of gender and emotion recognition proposed here is based on the SVM classifier. SVM [7,8,11] uses binary or multi-class classification. It uses hyper planes in the feature space of high dimensions.…”

Section: Classification Using Support Vector Machine (Svm)mentioning

confidence: 99%

See 3 more Smart Citations

Voice Feature Extraction for Gender and Emotion Recognition

et al. 2021

View full text Add to dashboard Cite

Voice recognition plays a key function in spoken communication that facilitates identifying the emotions of a person that reflects within the voice. Gender classification through speech is a popular Human Computer Interaction (HCI) method on account that determining gender through computer is hard. This led to the development of a model for "Voice feature extraction for Emotion and Gender Recognition". The speech signal consists of semantic information, speaker information (gender, age, emotional state), accompanied by noise. Females and males have specific vocal traits because of their acoustical and perceptual variations along with a variety of emotions which bring their own specific perceptions. In order to explore this area, feature extraction requires pre-processing of data, which is necessary for increasing the accuracy. The proposed model follows steps such as data extraction, pre-processing using Voice Activity Detector(VAD), feature extraction using Mel-Frequency Cepstral Coefficient(MFCC), feature reduction by Principal Component Analysis(PCA) and Support Vector Machine (SVM) classifier. The proposed combination of techniques produced better results which can be useful in healthcare sector, virtual assistants, security purposes and other fields related to Human Machine Interaction domain.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Section: Data Selectionmentioning

confidence: 99%

Section: Classification Using Support Vector Machine (Svm)mentioning

confidence: 99%

See 2 more Smart Citations

Voice Feature Extraction for Gender and Emotion Recognition

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The algorithm proposed by Humaid Alshamsi [4] [14], is used by the framework to extract features using MFCC frequency.…”

Section: Related Workmentioning

confidence: 99%

Speech Emotion Recognition using State-of-Art Learning Algorithms

Donepudi¹

2020

IJATCSE

View full text Add to dashboard Cite

Emotion is considered to be one of the significant human interaction factors. Recognizing human behavior based on emotion is often misinterpreted. However, that has not prevented the analysts from attempting to extract the information from a speech called speech recognition. In this paper, we analyzed the different algorithm's performance in the field of speech signal classification. Considering accuracy and precision as factors, ANN showed higher results with around 80% accuracy and correctness, followed by SVM and CNN competing for each other for accuracy in between 75 and 80 percent. SVM showed close approximation between accuracy and precision, leaving random forest classifier in the last place. Our experimentation showed neural networks performed substantially in the field of speech and signal processing.

show abstract