Improved Emotion Recognition With a Novel Speaker-Independent Feature
Authors:
- 3 April 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 14 (3) , 317-325
Abstract
Emotion recognition is one of the latest challenges in human-robot interaction. This paper describes the realization of emotional interaction for a Thinking Robot, focusing on speech emotion recognition. In general, speaker-independent systems show a lower accuracy rate compared with speaker-dependent systems, as emotional feature values depend on the speaker and their gender. However, speaker-independent systems are required for commercial applications. In this paper, a novel speaker-independent feature, the ratio of a spectral flatness measure to a spectral center (RSS), with a small variation in speakers when constructing a speaker-independent system is proposed. Gender and emotion are hierarchically classified by using the proposed feature (RSS), pitch, energy, and the mel frequency cepstral coefficients. An average recognition rate of 57.2% (plusmn 5.7%) at a 90% confidence interval is achieved with the proposed system in the speaker-independent mode.Keywords
This publication has 33 references indexed in Scilit:
- Clustering Documents with Active Learning Using Wikipedia2008
- Comparison of Classification Methods for Detecting Emotion from Mandarin SpeechIEICE Transactions on Information and Systems, 2008
- Emotional speech recognition: Resources, features, and methodsSpeech Communication, 2006
- Speaker model selection based on the Bayesian information criterion applied to unsupervised speaker indexingIEEE Transactions on Speech and Audio Processing, 2005
- Automatic emotional speech classification2004
- Construction of interactive movie system for multi-person participation2002
- Emotion in user interface, voice interaction system2002
- Emotion recognition in human-computer interactionIEEE Signal Processing Magazine, 2001
- Acoustical properties of speech as indicators of depression and suicidal riskIEEE Transactions on Biomedical Engineering, 2000
- An optimal orthonormal system for discriminant analysisPattern Recognition, 1985