Age Estimation in Short Speech Utterances Based on Bidirectional ‎Gated-Recurrent Neural Networks

Recently, age estimates from speech have received growing interest as they are important for ‎many applications like custom call routing, targeted marketing, or user-profiling. In this work, an ‎automatic system to estimate age in short speech utterances without ‎depending on the text is proposed. From each utterance frame, four ‎groups of features are extracted and then 10 statistical functionals are measured for each ‎extracted dimension of the features, to be followed by dimensionality reduction using Linear ‎Discriminant Analysis (LDA). Finally, bidirectional Gated-Recurrent Neural Networks (G-‎RNNs) are used to predict speaker age. Experiments are conducted on the VoxCeleb1 ‎dataset to show the performance of the proposed system, which is the first attempt to do so for ‎such a system. In gender-dependent system, the Mean Absolute Error (MAE) of the proposed system ‎is 9.25 years, and 10.33 ‎years, the Root Mean ‎Square Error (RMSE)‎ is 13.17 and 13.26, respectively, ‎for ‎female and male speakers. In gender_ independent system, the MAE of the proposed system is 10.96 years, and the RMSE is 15.47. The results show that the proposed system has a good performance on short-duration utterances, taking into consideration the high noise ratio in the VoxCeleb1 dataset. ‎

Affective Latent Representation of Acoustic and Lexical Features for Emotion Recognition

In this paper, we propose a novel emotion recognition method based on the underlying emotional characteristics extracted from a conditional adversarial auto-encoder (CAAE), in which both acoustic and lexical features are used as inputs. The acoustic features are generated by calculating statistical functionals of low-level descriptors and by a deep neural network (DNN). These acoustic features are concatenated with three types of lexical features extracted from the text, which are a sparse representation, a distributed representation, and an affective lexicon-based dimensions. Two-dimensional latent representations similar to vectors in the valence-arousal space are obtained by a CAAE, which can be directly mapped into the emotional classes without the need for a sophisticated classifier. In contrast to the previous attempt to a CAAE using only acoustic features, the proposed approach could enhance the performance of the emotion recognition because combined acoustic and lexical features provide enough discriminant power. Experimental results on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) corpus showed that our method outperformed the previously reported best results on the same corpus, achieving 76.72% in the unweighted average recall.

Speech emotion classification using fractal dimension-based features

During the last 10–20 years, a great deal of new ideas have been proposed to improve the accuracy of speech emotion recognition: e.g., effective feature sets, complex classification schemes, and multi-modal data acquisition. Nevertheless, speech emotion recognition is still the task in limited success. Considering the nonlinear and fluctuating nature of the emotional speech, in this paper, we present fractal dimension-based features for speech emotion classification. We employed Katz, Castiglioni, Higuchi, and Hurst exponent-based features and their statistical functionals to establish the 224-dimensional full feature set. The dimension was downsized by applying the Sequential Forward Selection technique. The results of experimental study show a clear superiority of fractal dimension-based feature sets against the acoustic ones. The average accuracy of 96.5% was obtained using the reduced feature sets. The feature selection enabled us to obtain the 4-dimensional and 8-dimensional sets for Lithuanian and German emotions, respectively.

Dynamical equations and Lagrange–Ricci flow evolution on prolongation Lie algebroids

The approach to nonholonomic Ricci flows and geometric evolution of regular Lagrange systems (S. Vacaru. J. Math. Phys. 49, 043504 (2008); Ibid. Rep. Math. Phys. 63, 95 (2009)) is extended to include geometric mechanics and gravity models on Lie algebroids. We prove that such evolution scenarios of geometric mechanics and analogous gravity can be modeled as gradient flows characterized by generalized Perelman functionals if an equivalent geometrization of Lagrange mechanics (J. Kern. Arch. Math. (Basel), 25, 438 (1974)) is considered. The Hamilton equations on Lie algebroids describing Lagrange–Ricci flows are derived. Finally, we show that geometric evolution models on Lie algebroids are described by effective thermodynamical values derived from statistical functionals on prolongation Lie algebroids.

Bootstrapping Average Value at Risk of Single and Collective Risks

Almost sure bootstrap consistency of the blockwise bootstrap for the Average Value at Risk of single risks is established for strictly stationary β -mixing observations. Moreover, almost sure bootstrap consistency of a multiplier bootstrap for the Average Value at Risk of collective risks is established for independent observations. The main results rely on a new functional delta-method for the almost sure bootstrap of uniformly quasi-Hadamard differentiable statistical functionals, to be presented here. The latter seems to be interesting in its own right.