Content area
Full text
Telecommun Syst (2013) 52:14671478 DOI 10.1007/s11235-011-9624-z
Speech emotion recognition approaches in human computer interaction
S. Ramakrishnan Ibrahiem M.M. El Emary
Published online: 2 September 2011 Springer Science+Business Media, LLC 2011
Abstract Speech Emotion Recognition (SER) represents one of the emerging elds in human-computer interaction. Quality of the human-computer interface that mimics human speech emotions relies heavily on the types of features used and also on the classier employed for recognition. The main purpose of this paper is to present a wide range of features employed for speech emotion recognition and the acoustic characteristics of those features. Also in this paper, we analyze the performance in terms of some important parameters such as: precision, recall, F -measure and recognition rate of the features using two of the commonly used emotional speech databases namely Berlin emotional database and Danish emotional database. Emotional speech recognition is being applied in modern human-computer interfaces and the overview of 10 interesting applications is also presented in this paper to illustrate the importance of this technique.
Keywords Speech emotion Human-computer interface
Pitch and emotion recognition
1 Introduction
Understanding emotions is essential in human social interactions. Studies suggest that only 10% of human life is completely unemotional. Although having been studied since the
S. Ramakrishnan ( )
Information Tech. Dep., Dr. Mahalingam College of Eng. & Tech., Udumalai Road, Pollachi 642003, Indiae-mail: mailto:[email protected]
Web End [email protected]
I.M.M. El EmaryFaculty of Information Technology, King Abdulaziz University, P.O. Box 18388, Jeddah, King Saudi Arabiae-mail: mailto:[email protected]
Web End [email protected]
1950s, the investigation of emotional cues has made considerable advances in the last years [1, 2]. This is mainly due to the new application developments with respect to human-machine, human-robot interfaces and multimedia retrieval. From the technological point of view the reasons for the renewed interests are also due to: technological progress in recording, storing, and processing audio and visual information; the development of non-intrusive sensors; the advent of wearable computers; the urge to enrich human-computer interface from point-and-click to sense-and-feel.
Emotion-oriented computing aims at the automatic recognition and synthesis of emotions in speech, facial expression, or any other biological channel [312]. Research about automated recognition of emotions in facial expressions is very rich [1, 1316]. However, emotion recognition using facial recognition is computationally complex, because of...