Speech synthesis system based on mixed hidden Markov model

Abstract

The invention relates to a voice synthesis system based on a mixing hidden Markov model, wherein a frequency spectrum information generating module receives any text information, selects the codebook vector which represents frequency spectrum information and outputs the frequency spectrum information, a base frequency information generating module receives the text information, takes charge of predicting the pitch change of a to-be synthetic sentence and outputs a base frequency curve, a parameter voice synthesizer module receives the frequency spectrum information of the frequency spectrum information generating module and the base frequency information of the base frequency information generating module, outputs the synthesized voice results, an off-line training module takes charge of training various hidden Markov models, a discrete hidden Markov model obtains the output probability of the real frequency spectrum vector, guarantees the accuracy of the frequency spectrum information, and the frequency spectrum guaranteed by the codebook choosing arithmetic can not generate the oversmoothing phenomenon of time-domain. Using the system to improve the articulation of the output voice of the parameter voice synthesis system, the fidelity of the output voice is greatly improved, which is almost close to the voice quality based on a splicing voice synthesis system.

Description

technical field [0001] The present invention relates to a speech synthesis system, in particular to a speech synthesis system based on a hybrid hidden Markov model. Background technique [0002] Speech synthesis system, also known as text-to-speech conversion system (TTS system), its main function is to convert any text string received or input by the computer into speech output. The traditional speech synthesis system is based on unit splicing, and its sound quality is good, but the required sound library resources are relatively large, which causes its application in embedded devices to encounter bottlenecks. The speech synthesis system based on Hidden Markov Model is essentially a parametric synthesis system, which has the advantages of high flexibility and small storage resources. However, due to the nature of its parameterization, its sound quality performance is usually much worse than that of the splicing-based synthesis system, which is also the bottleneck of the cu...

AI Technical Summary

Problems solved by technology

If a certain state lasts for a long time, only relying on the mean value of the Gaussian function corresponding to the state cannot describe the details of the speech parameter changes in the state, which causes a serious time-domain over-smoothing problem

Images