Auditory Representation Learning

Abstract

Representation learning (RL) or feature learning has a huge impact in the field newlineof signal processing applications. The goal of the RL approaches is to learn the newlinemeaningful representation directly from the data that can be helpful to the pattern newlineclassifier. Specifically, the unsupervised RL has gained a significant interest in newlinethe feature learning in various signal processing areas including the speech and newlineaudio processing. Recently, various RL methods are used to learn the auditory like newlinerepresentations from the speech signals or its spectral representations. In this thesis, we propose a novel auditory representation learning model based on the Convolutional Restricted Boltzmann Machine (ConvRBM). The auditory like sub band filters are learned when the model is trained directly on the raw newlinespeech and audio signals with arbitrary lengths. newline