Feature Selection for Speech Emotion Recognition in Spanish and Basque: On the Use of Machine Learning to Improve Human-Computer Interaction

Study of emotions in human-computer interaction is a growing research area. This paper shows an attempt to select the most significant features for emotion recognition in spoken Basque and Spanish Languages using different methods for feature selection. RekEmozio database was used as the experimental data set. Several Machine Learning paradigms were used for the emotion classification task. Experiments were executed in three phases, using different sets of features as classification variables in each phase. Moreover, feature subset selection was applied at each phase in order to seek for the most relevant feature subset. The three phases approach was selected to check the validity of the proposed approach. Achieved results show that an instance-based learning algorithm using feature subset selection techniques based on evolutionary algorithms is the best Machine Learning paradigm in automatic emotion recognition, with all different feature sets, obtaining a mean of 80,05% emotion recognition rate in Basque and a 74,82% in Spanish. In order to check the goodness of the proposed process, a greedy searching approach (FSS-Forward) has been applied and a comparison between them is provided. Based on achieved results, a set of most relevant non-speaker dependent features is proposed for both languages and new perspectives are suggested.

A unifying resolution-independent formulation for early vision

We present a model for early vision tasks such as denoising, super-resolution, deblurring, and demosaicing. The model provides a resolution-independent representation of discrete images which admits a truly rotationally invariant prior. The model generalizes several existing approaches: variational methods, finite element methods, and discrete random fields. The primary contribution is a novel energy functional which has not previously been written down, which combines the discrete measurements from pixels with a continuous-domain world viewed through continous-domain point-spread functions. The value of the functional is that simple priors (such as total variation and generalizations) on the continous-domain world become realistic priors on the sampled images. We show that despite its apparent complexity, optimization of this model depends on just a few computational primitives, which although tedious to derive, can now be reused in many domains. We define a set of optimization algorithms which greatly overcome the apparent complexity of this model, and make possible its practical application. New experimental results include infinite-resolution upsampling, and a method for obtaining subpixel superpixels. © 2012 IEEE.

Learning based automatic face annotation for arbitrary poses and expressions from frontal images only

Statistical approaches for building non-rigid deformable models, such as the Active Appearance Model (AAM), have enjoyed great popularity in recent years, but typically require tedious manual annotation of training images. In this paper, a learning based approach for the automatic annotation of visually deformable objects from a single annotated frontal image is presented and demonstrated on the example of automatically annotating face images that can be used for building AAMs for fitting and tracking. This approach employs the idea of initially learning the correspondences between landmarks in a frontal image and a set of training images with a face in arbitrary poses. Using this learner, virtual images of unseen faces at any arbitrary pose for which the learner was trained can be reconstructed by predicting the new landmark locations and warping the texture from the frontal image. View-based AAMs are then built from the virtual images and used for automatically annotating unseen images, including images of different facial expressions, at any random pose within the maximum range spanned by the virtually reconstructed images. The approach is experimentally validated by automatically annotating face images from three different databases. © 2009 IEEE.

Expressive visual text-to-speech using active appearance models

This paper presents a complete system for expressive visual text-to-speech (VTTS), which is capable of producing expressive output, in the form of a 'talking head', given an input text and a set of continuous expression weights. The face is modeled using an active appearance model (AAM), and several extensions are proposed which make it more applicable to the task of VTTS. The model allows for normalization with respect to both pose and blink state which significantly reduces artifacts in the resulting synthesized sequences. We demonstrate quantitative improvements in terms of reconstruction error over a million frames, as well as in large-scale user studies, comparing the output of different systems. © 2013 IEEE.

Behavioral responses of tilapia (Oreochromis niloticus) to acute fluctuations in dissolved oxygen levels as monitored by computer vision

Behavioral and ventilatory parameters have the possibility of predicting the stress state of fish in vivo and in situ. This paper presents a new image-processing algorithm for quantifying the average swimming speed of a fish school in an aquarium. This method is based on the alteration in projected area caused by the movement of individual fish during frame sequences captured at given time intervals. The image enhancement method increases the contrast between fish and background, and is thus suitable for use in turbid aquaculture water. Behavioral parameters (swimming activity and distribution parameters) and changes in ventilation frequency (VF) of tilapia (Oreochromis niloticus) responded to acute fluctuations in dissolved oxygen (DO) which were monitored continuously in the course of normoxia, falling DO level, maintenance of hypoxia (three levels of 1.5, 0.8 and 0.3 mg l(-1)) and subsequent recovery to normoxia. These parameters responded sensitively to acute variations in DO level; they displayed significant changes (P < 0.05) during severe hypoxia (0.8 and 0.3 mg l(-1) level) compared with normoxic condition, but there was no significant difference under conditions of mild hypoxia (1.5 mg l(-1) level). There was no significant difference in VF between two levels of severe hypoxia 0.8 and 0.3 mg l(-1) level during the low DO condition. The activity and distribution parameters displayed distinguishable differences between the 0.8 and 0.3 mg l(-1) levels. The behavioral parameters are thus capable of distinguishing between different degrees of severe hypoxia, though there were relatively large fluctuations. (c) 2006 Elsevier B.V. All rights reserved.