Emotional Pitch Template-based Emotional Speech Synthesis

With the rapid development of information technology, human dependence on computer is growing.Therefore,human-computer interaction capabilities get more and more attention of researchers.Voice has the largest information capacity in many information carrier, with the highest level of intelligence.Traditional voice processing systems focus on the accuracy of voice only, ignoring the emotional factors contained in the voice signal.Let computer speak emotional voice like people is people's long-term goal.Therefore, this article studied on emotional speech synthesis techniques.The paper presents a method of emotional speech synthesis based on the emotional pitch template Overlap.The paper extracted initial templates and happy, angry, sad and neutral vowels pitch templates from emotional speech database recorded by Chinese Academy of Sciences using praat software, established initial library and emotional vowel pitch template library; established the normalized tone model function of Chinese four tones,and studied how to get the pitch period sequence through the tone mode function; studied the effect of emotional pitch template to the quality of synthetic speech; extracted the emotional speech prosody parameters and sdudied performance of prosodic features under a variety of emotions; studied Pitch Synchronous Overlap Algorithm,and proposed an algorithm based on the emotional pitch template overlap to synthesis emotional speech. The algorithm use the emotional pitch template to be the synthesis elements,synthesis the speech based on the tone and the statistical laws of emotional features. Simulation results show that the emotional speech synthesized by the targeted emotional pitch template has the tone color of the targeted emotion.After the adjustment of prosodic parameters,we can get the ideal emotional speech.Compared with the traditional emotional speech synthesis method, the method based on emotional pitch overlap is more easy, the synthetic speech is more clear and has more emotional colors.The method will increase the intelligence of Speech synthesis system and improve the capabilities of human-computer interaction.