Skip to Main Content
The separation of noise from speech has always been a necessary requirement and is being demanded in audio signal processing as an important factor to achieve a dear message in voice communication. In the literature, some traditional methods that has been employed include machine learning softwares with basic algorithms. However, with the accelerated development in the field of computer technology especially the artificial intelligence, application of machine learning softwares and neural networks in the domain of audio signal processing is still a fascinating field for researchers. This paper provides an experimental simulation of speech with and with out noise using different neural networks to solve the filtering problem. In the course of this research, first an FIR digital filter is designed, since an FIR filter provides a fast convergence and give results near the global optimal. The neural networks such as Elman, perceptron and radial base function are then trained with different training algorithms and compared with the performance of FIR digital filter including their computational complexity. The experimental results exhibits that training/learning junctions chosen to train the neural network are very important to the final results.