Earticle

초록

영어

Speech Emotion Recognition (SER) is a hot research topic in the field of Human Computer Interaction (HCI). In this paper, we recognize three emotional states: happy, sad and neutral. The explored features include: energy, pitch, linear predictive spectrum coding (LPCC), mel-frequency spectrum coefficients (MFCC), and mel-energy spectrum dynamic coefficients (MEDC). A German Corpus (Berlin Database of Emotional Speech) and our self-built Chinese emotional databases are used for training the Support Vector Machine (SVM) classifier. Finally results for different combination of the features and on different databases are compared and explained. The overall experimental results reveal that the feature combination of MFCC+MEDC+ Energy has the highest accuracy rate on both Chinese emotional database (91.3% ) and Berlin emotional database (95.1% ).

목차

Abstract
 1. Introduction
 2. Speech Database
 3. Speech Emotion Recognition System
 4. Feature Extraction
  4.1. Energy and Related Features
  4.2. Pitch and Related Features
  4.3. Linear Prediction Cepstrum Coefficients (LPCC)
  4.4. Mel-Frequency Cepstrum Coefficients (MFCC)
  4.5. Mel Energy Spectrum Dynamic coefficients (MEDC)
 5. Experiment and Results
  5.1. SVM Classification Algorithm
  5.2. Training Models
  5.3. Experimental Results
 6. Conclusion and Future Works
 References

키워드

저자

• Yixiong Pan [ Department of Computer Technology Shanghai JiaoTong University, Shanghai, China ]
• Peipei Shen [ Department of Computer Technology Shanghai JiaoTong University, Shanghai, China ]
• Liping Shen [ Department of Computer Technology Shanghai JiaoTong University, Shanghai, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Smart Home

• 간기

  격월간

• pISSN

  1975-4094

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605