Different Sentiment Analysis of Text-to-Speech Synthesize Using Fuzzy Neural Network for English

In urbanized countries, the customer service with automated system in speech synthesis has been the recent trend. A novel technique like Fuzzy Neural Network (FNN) based TTS system for the English language has been proposed for improve the naturalness of the automated speech synthesis systems. Different emotional sentences expressing “Happy”, “Fear”, “Neutral” and “Sad” have been given as input for this system. Depends on the emotions, it uses a group of fuzzy rules to segregate the sentences to recognize the respective emotions. The drawbacks of neural network has been eliminated by FNN incorporated in TTS system. It assigns specific labels for different emotions. Then the suitable emotion based speech output has been generated from the system. The genuineness of the FNN based TTS output is calculated through the comparative performance analysis with respect to the recorded human speech in the noise free environment. The spectral mismatch and amplitude variations of the resultant waves plays an vital task to measure the genuineness of the TTS output.