Towards Advanced Speech Signal Processing: A Statistical Perspective on Convolution-Based Architectures and its Applications
This is an incremental survey paper for researchers in speech technology, providing a comparative analysis of existing models without introducing new methods.
This survey paper compares convolution-based architectures (CNNs, Conformers, ResNets, CRNNs) for speech signal processing tasks like speech recognition and emotion recognition, analyzing their training costs, model sizes, accuracy, and speed to identify strengths, weaknesses, and research directions.
This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker identification, emotion recognition, and speech enhancement applications. Through comparative training cost assessment, model size, accuracy and speed assessment, we compare the strengths and weaknesses of each model, identify potential errors and propose avenues for further research, emphasizing the central role it plays in advancing applications of speech technologies.