HMM-Based Text-to-Speech Synthesis &amp; Stressed Speech Processing

Pradnya Prakash Wagh; Swati Warungase; Neha Ashok Aringale; Nadeem Bhaimiya Shaikh

doi:10.37591/rtecs.v10i3.7812

Abstract

According to this paper, the new system produces synthetic speech that is noticeably higher-quality thanspeaker-dependent systems when actual speech data sets are used, and it can compete with speaker-dependent approacheseven in situations when substantial speech data sets are available. This excitation signal, the glottal source, has naturallypiqued the interest of speech synthesis, and a variety of techniques have been developed to mimic the glottal source ofspontaneous speech.The use of artificial models for the glottal source has improved the synthesis's quality. However, thecurrent models also oversimplify the glottal source, which has resulted in inadequate synthesis quality. Using glottal inversefiltering to recover glottal flow pulses from natural speech has been proposed as a solution to problems arising fromsimplistic glottal source models. However, previous work with glottal flow pulses extracted from real speech is limited tocertain applications, such as vowel isolation, and the benefits of combining automatic glottal inverse filtering with an HMM-based speech synthesizer have not been explored. Furthermore, a comparative analysis using many speech synthesismethods demonstrates how reliable the new approach is: Even for sentences that are outside of its area, it can create voicesfrom less-than-ideal speech data and synthesize high-quality speech.