Analyzing temporal properties of speech trajectory using graph structures towards speech recognition

Abstract

Speech signal analysis aims to identify patterns within data to develop effec tive recognition algorithms. This process primarily utilizes feature extraction techniques such as linear predictive coding (LPC), linear predictive cepstral co efficients (LPCCs), and Mel-frequency cepstral coefficients (MFCCs). These features are crucial for constructing recognition algorithms that leverage both statistical and deep learning methods. While deep learning models require ex tensive datasets, they often prove unsuitable for low-resource languages. The Hidden Markov model (HMM)is the most widely adopted statistical framework in speech processing. However, HMMs are characterized by state-dependent models, where each state interacts only with its neighboring states. This limita tion restricts HMMs from capturing long-term signal properties, highlighting the need for addressing these constraints at the feature extraction stage. Most feature extraction methods rely on short-term signal processing, which further limits the comprehension of speech utterances. To overcome these limitations, alter native methods are necessary to capture more comprehensive patterns. This pa per presents a graph-based approach for analyzing speech trajectories and their temporal properties, which are subsequently validated using HMMs in speech recognition tasks. Graph-based representations on a low-resource Telugu dataset improve recognition accuracy by 13% while reducing processing time compared to traditional LPC.