Graph Eigenvalue based Structural Method towards Phonetic Boundary Detection

Phoneme boundary analysis is an important prob-lem in the domain of speech processing to identify the bound-aries between different phonetic units. It has significance in the annotation of data sets and in recognition systems as well. This problem has been addressed by various frameworks such as Hidden Markov Modeling, Artificial Neural Networks, and Deep Learning. Even though they are effective, the task is challenging for zero or low resource languages because of the less availability of data sets. Moreover, the methods that do not rely on training processes are desirable because they can produce the required results with less amount of data. In this paper, a graph-based segmentation framework for phoneme boundary detection that uses structural properties and graph eigenvalues is proposed. The method identifies the boundary points in a single scan by using the temporal and spectral variations represented as graph eigenvalues. The method is proven to be effective on a sample data set of Indian accented English words. The proposed method with detailed analysis is presented in the paper.