Designing Simple Nonlinear Filters Using Hysteresis of Single Recurrent Neurons for Acoustic Signal Recognition in Robots
نویسندگان
چکیده
In this article we exploit the discrete-time dynamics of a single neuron with self-connection to systematically design simple signal filters. Due to hysteresis effects and transient dynamics, this single neuron behaves as an adjustable low-pass filter for specific parameter configurations. Extending this neuro-module by two more recurrent neurons leads to versatile highand band-pass filters. The approach presented here helps to understand how the dynamical properties of recurrent neural networks can be used for filter design. Furthermore, it gives guidance to a new way of implementing sensory preprocessing for acoustic signal recognition in autonomous robots.
منابع مشابه
Persian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملNonlinear Stabilizing Controller for a Special Class of Single Link Flexible Joint Robots
Joint flexibility is a very important factor to consider in the controller design for robot manipulators if high performance is expected. Most of the research works on control of flexible-joint robots in literature have ignored the actuator dynamics to avoid complexity in controller design. The problem of designing nonlinear controller for a class of single-link flexible-joint robot manipulator...
متن کاملDesign of IIR Digital Filter using Modified Chaotic Orthogonal Imperialist Competitive Algorithm (RESEARCH NOTE)
There are two types of digital filters including Infinite Impulse Response (IIR) and Finite Impulse Response (FIR). IIR filters attract more attention as they can decrease the filter order significantly compared to FIR filters. Owing to multi-modal error surface, simple powerful optimization techniques should be utilized in designing IIR digital filters to avoid local minimum. Imperialist compe...
متن کاملشبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملA simple method for designing high-quality prototype filters for M-band pseudo QMF banks
AbsCmct-This correspondence discusses a new method for designing the prototype filters necessary to implement M-band pseudo QMF banks. This method does not rely on the traditional nonlinear optimization used in past work but rather optimizes a single parameter on a convex error surface, consistently delivering the best equiripple filter possible while minimizing the overlapped passband distortion.
متن کامل