Results 11 to 20 of about 2,795,142 (309)
Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models [PDF]
, 2010 Hidden Markov model (HMM) -based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset ...
core +9 more sources
Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction [PDF]
, 2010 This paper demonstrates how unsupervised cross-lingual adaptation of HMM-based speech synthesis models may be performed without explicit knowledge of the adaptation data language.
Teemu Hirsimaki +5 more
core +2 more sources
IEEE Access, 2019 Feedforward neural network (FNN) is one of the most widely used and fastest-developed artificial neural networks. Much evolutionary computation (EC) methods have been used to optimize the weights of FNN.
Yu Xue, Tao Tang, Alex X. Liu
doaj +1 more source
Journal of Intelligent Systems, 2023 This study based on the standard differential evolution (DE) algorithm was carried out to address the issues of control parameter imprinting, mutation process, and crossover process in the standard DE algorithm as well as the issue of multidimensional ...
Wu Wenchang
doaj +1 more source
Моделирование и анализ информационных систем, 2020 Self-adjustment of parameters can significantly improve the performance of evolutionary algorithms. A notable example is the (1 + (λ,λ)) genetic algorithm, where adaptation of the population size helps to achieve the linear running time on the OneMax ...
Anton Olegovich Bassin +2 more
doaj +1 more source
Crossover Rate Sorting in Adaptive Differential Evolution
Algorithms, 2023 Differential evolution (DE) is a popular and efficient heuristic numerical optimization algorithm that has found many applications in various fields. One of the main disadvantages of DE is its sensitivity to parameter values.
Vladimir Stanovov +2 more
doaj +1 more source
Surrogate-Assisted Automatic Parameter Adaptation Design for Differential Evolution
Mathematics, 2023 In this study, parameter adaptation methods for differential evolution are automatically designed using a surrogate approach. In particular, Taylor series are applied to model the searched dependence between the algorithm’s parameters and values ...
Vladimir Stanovov, Eugene Semenkin
doaj +1 more source
Neuroevolution for Parameter Adaptation in Differential Evolution
Algorithms, 2022 Parameter adaptation is one of the key research fields in the area of evolutionary computation. In this study, the application of neuroevolution of augmented topologies to design efficient parameter adaptation techniques for differential evolution is ...
Vladimir Stanovov +2 more
doaj +1 more source
The Automatic Design of Multimode Resonator Topology with Evolutionary Algorithms
Sensors, 2022 Microwave electromagnetic devices have been used for many applications in tropospheric communication, navigation, radar systems, and measurement. The development of the signal preprocessing units including frequency-selective devices (bandpass filters ...
Vladimir V. Stanovov +3 more
doaj +1 more source
Energy-Efficient Optimization Method of Urban Rail Train Based on Following Consistency
Energies, 2023 Because of the short distance between stations in urban rail transit, frequent braking of urban rail trains during operation will generate a large amount of regenerative braking energy.
Ruxun Xu +3 more
doaj +1 more source