SVM based Emotional Speaker Recognition using MFCC-SDC Features

Abstract

Enhancing the performance of emotional speaker recognition process has witnessed an increasing interest in the last years. This paper highlights a methodology for speaker recognition under different emotional states based on the mul-ticlass Support Vector Machine (SVM) classifier. We compare two feature extraction methods which are used to represent emotional speech utterances in order to obtain best accuracies. The first method known as traditional Mel-Frequency Cepstral Coefficients (MFCC) and the second one is MFCC combined with Shifted-Delta-Cepstra (MFCC-SDC). Experimentations are conducted on IEMOCAP database using two multiclass SVM ap-proaches: One-Against-One (OAO) and One Against-All (OAA). Obtained results show that MFCC-SDC features outperform the conventional MFCC.

Authors and Affiliations

Asma Mansour, Zied Lachiri

Keywords

Related Articles

Enhancing Wireless Sensor Network Security using Artificial Neural Network based Trust Model

Wireless sensor network (WSN) is widely used in environmental conditions where the systems depend on sensing and monitoring approach. Water pollution monitoring system depends on a network of wireless sensing nodes which...

Phishing Website Detection based on Supervised Machine Learning with Wrapper Features Selection

The problem of Web phishing attacks has grown considerably in recent years and phishing is considered as one of the most dangerous Web crimes, which may cause tremendous and negative effects on online business. In a Web...

SDME Quality Measure based Stopping Criteria for Iterative Deblurring Algorithms

Deblurring from motion problem with or without noise is ill-posed inverse problem and almost all inverse problem require some sort of parameter selection. Quality of restored image in iterative motion deblurring is depen...

A Novel Design of Patch Antenna using U-Slot and Defected Ground Structure

A novel design of patch antenna is presented with double U slot structure on patch with ground irregularities. As a result tri-band response is achieved with gain reaching 0.785 to 3.75dB respectively and directivity of...

A Blockchain Technology Evolution Between Business Process Management (BPM) and Internet-of-Things (IoT)

A Blockchain is considered the main mechanism for Bitcoin concurrency. A Blockchain is known by a public ledger and public transactions stored in a chain. The properties of blockchain demonstrate in decentralization as d...

Download PDF file
  • EP ID EP258416
  • DOI 10.14569/IJACSA.2017.080471
  • Views 106
  • Downloads 0

How To Cite

Asma Mansour, Zied Lachiri (2017). SVM based Emotional Speaker Recognition using MFCC-SDC Features. International Journal of Advanced Computer Science & Applications, 8(4), 538-544. https://europub.co.uk/articles/-A-258416