Emotion recognition from speech signals via a probabilistic echo-state network (bibtex)
by Trentin, Edmondo, Scherer, Stefan and Schwenker, Friedhelm
Abstract:
The paper presents a probabilistic echo-state network (π -ESN) for density estimation over variable-length sequences of multivariate random vectors. The π -ESN stems from the combination of the reservoir of an ESN and a parametric density model based on radial basis functions. A constrained maximum likelihood training algorithm is introduced, suitable for sequence classification. Extensions of the algorithm to unsupervised clustering and semi-supervised learning (SSL) of sequences are proposed. Experiments in emotion recognition from speech signals are conducted on the WaSeP© dataset. Compared with established techniques, the π -ESN yields the highest recognition accuracies, and shows interesting clustering and SSL capabilities.
Reference:
Emotion recognition from speech signals via a probabilistic echo-state network (Trentin, Edmondo, Scherer, Stefan and Schwenker, Friedhelm), In Pattern Recognition Letters, volume 66, 2014.
Bibtex Entry:
@article{trentin_emotion_2014,
	title = {Emotion recognition from speech signals via a probabilistic echo-state network},
	volume = {66},
	url = {http://www.sciencedirect.com/science/article/pii/S0167865514003328},
	doi = {dx.doi.org/10.1016/j.patrec.2014.10.015},
	abstract = {The paper presents a probabilistic echo-state network (π -ESN) for density estimation over variable-length sequences of multivariate random vectors. The π -ESN stems from the combination of the reservoir of an ESN and a parametric density model based on radial basis functions. A constrained maximum likelihood training algorithm is introduced, suitable for  sequence classification. Extensions of the algorithm to  unsupervised clustering and semi-supervised learning (SSL) of sequences are proposed. Experiments in emotion recognition from speech signals are conducted on the WaSeP© dataset. Compared with established techniques, the π -ESN yields the highest recognition accuracies, and shows interesting clustering and SSL capabilities.},
	journal = {Pattern Recognition Letters},
	author = {Trentin, Edmondo and Scherer, Stefan and Schwenker, Friedhelm},
	month = nov,
	year = {2014},
	keywords = {Virtual Humans},
	pages = {4 --12}
}
Powered by bibtexbrowser