No abstract

No abstract

In this study, the focus is on the search for a model that is articulatorily possible and perceptually plausible. A high-quality nasal sound synthesis structure in the acoustic domain, with a parallel formant synthesizer, that includes nasal articulation effects and defines independent acoustic parameters which are the basis of perceptual studies, has been obtained. A pole-zero-pole structure combined with a bank of formants is proposed as a high-quality nasal vowel synthesizer. A set of perceptual tests is conducted to test nasality variation with nasal synthesis eigenparameters. The results of tests are used to establish a new model describing [+ nasal]. Based on this model, the nature of the French nasal vowel and its distributional properties are discussed. Finally, nasality variation is tested at the auditory-nerve level with the help of a model of the peripheral auditory system. The neural firing pattern and the synchronization index pattern are discussed in terms of the nasality model established.

No abstract

Credible and accurate traffic flow forecasting is critical for deploying intelligent traffic management systems. Nevertheless, it remains challenging to develop a robust and efficient forecasting model due to the nonlinear characteristics and inherent stochastic traffic flow. Aiming at the nonlinear relationship in the traffic flow for different scenarios, we proposed a two-stage hybrid extreme learning model for short-term traffic flow forecasting. In the first stage, the particle swarm optimization algorithm is employed for determining the initial population distribution of the gravitational search algorithm to improve the efficiency of the global optimal value search. In the second stage, the results of the previous stage, rather than the network structure parameters randomly generated by the extreme learning machine, are used to train the hybrid forecasting model in a data-driven fashion. We evaluated the trained model on four real-world benchmark datasets from highways A1, A2, A4, and A8 connecting the Amsterdam ring road. The RMSEs of the proposed model are 288.03, 204.09, 220.52, and 163.92, respectively, and the MAPEs of the proposed model are 11.53%, 10.16%, 11.67%, and 12.02%, respectively. Experimental results demonstrate the superior performance of our proposed model.