Abstract
Arabic Automatic Speech Recognition Based on Emotion Detection
Highlights
Emotion is a complex psychological state that governs our daily lives
Several studies have proposed acoustic features from a speech which well suited the emotional information from speech, such as pitch, energy, formant frequency [4], linear prediction cepstrum coefficients (LPCC) [5], LSP, MFCC [6]–[9], and Mel filter bank (MFB) [10]
The early classification algorithms for Automatic speech emotion recognition (ASER) based on the conventional machine learning algorithms such as k-Nearest Neighbor (KNN) [11], support vector machine (SVM) [12], artificial neural network (ANN) [13], Gaussian Mixture Model (GMM) [14], and Hidden Markov Model (HMM) [15] have been used by many researchers
Summary
Emotion is a complex psychological state that governs our daily lives. Understanding emotion and explore how people react enriches the interaction [1]. We work on the features of emotion in speech. We focus on identifying the best speech features and models for recognizing three emotional states from Arabic speech: happy, angry, and surprised. The research activities on ASER face many challenges like the various dialects, the complexity of phonetic rules of the Arabic language. Several studies have proposed acoustic features from a speech which well suited the emotional information from speech, such as pitch, energy, formant frequency [4], linear prediction cepstrum coefficients (LPCC) [5], LSP, MFCC [6]–[9], and Mel filter bank (MFB) [10].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
