A novel real-time emotion detection system from audio streams based on Bayesian Quadratic Discriminate Classifier for ADAS

Machot, Fadi Al; Mosa, Ahmad Haj; Dabbour, Kosai; Fasih, Alireza; Schwarzlmüller, Christopher; Ali, Mouhanndad Ali; Kyamakya, Kyandoghere

doi:10.1109/inds.2011.6024783

Cited by 25 publications

(29 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To train our emotion classification system as well as to test its performance, we select two speech emotion analysis datasets, which are the LDC dataset Liberman et al (2002) and the UGA dataset Bri (2016). A few samples of the speech utterances from the LDC and the UGA datasets are available on the University of Rochester Wireless Communications and Networking Group's website Bri (2016), to provide readers with a better understanding of these two datasets.…”

Section: Ldc and Uga Datasetsmentioning

confidence: 99%

“…A few samples of the speech utterances from the LDC and the UGA datasets are available on the University of Rochester Wireless Communications and Networking Group's website Bri (2016), to provide readers with a better understanding of these two datasets.…”

Section: Ldc and Uga Datasetsmentioning

confidence: 99%

“…Our method achieves a decision-level correct classification rate of 80% for six emotions using the LDC dataset Liberman et al (2002) spoken by actors and actresses, and 45% on a noisy dataset spoken by ordinary speakers using the UGA dataset Bri (2016). Our system outperforms a state-of-the-art method proposed in Rachuri et al (2010), which achieves a decision-level correct classification rate of 71% for classifying five emotions based on the same LDC dataset.…”

Section: Introductionmentioning

confidence: 96%

“…Call centers employ emotion classification to prioritize impatient customers Gupta and Rajput (2007) Lee and Narayanan (2005). Warning systems have been developed to detect aggressive driving Al Machot et al (2011) or to keep the driver alert Schuller et al (2004). In the healthcare field, emotion classification is used by clinicians for assessment or treatment of patients with psychological disorders or conditions that create emotional difficulties, such as autism or depression Tacconi et al (2008) Cowie et al (2000).…”

Section: Introductionmentioning

confidence: 99%

“…Hence, this proposed system can potentially replace humans in classifying emotions in scenarios where humans cannot be easily trained. The MATLAB code for our emotion classification system is available on the University of Rochester Wireless Communications and Networking Group's website Bri (2016).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Enhanced multiclass SVM with thresholding fusion for speech-based emotion classification

Yang

Yuan

Zhou

et al. 2016

Int J Speech Technol

View full text Add to dashboard Cite

As an essential approach to understanding human interactions, emotion classification is a vital component of behavioral studies as well as being important in the design of context-aware systems. Recent studies have shown that speech contains rich information about emotion, and numerous speech-based emotion classification methods have been proposed. However, the classification performance is still short of what is desired for the algorithms to be used in real systems. We present an emotion classification system using several one-againstall support vector machines with a thresholding fusion mechanism to combine the individual outputs, which provides the functionality to effectively increase the emotion classification accuracy at the expense of rejecting some samples as unclassified. Results show that the proposed system outperforms three stateof-the-art methods and that the thresholding fusion mechanism can effectively improve the emotion classification, which is important for applications that require very high accuracy but do not require that all samples be classified.We evaluate the system performance for several challenging scenarios including speaker-independent tests, tests on noisy speech signals, and tests using non-professional acted recordings, in order to demonstrate the performance of the system and the effectiveness of the thresholding fusion mechanism in real scenarios.

show abstract

Section: Ldc and Uga Datasetsmentioning

confidence: 99%

Section: Ldc and Uga Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%