High-quality voice conversion method based on modeling of signal timing characteristics

Abstract

The invention discloses a high-quality voice conversion method based on modeling of signal timing characteristics. The high-quality voice conversion method based on the modeling of the signal timing characteristics comprises the following steps: aiming at parallel data of a source and a target, considering modeling and tracing the timing characteristics of the source and the target, utilizing the hybrid Kalman filter, estimating structural parameters of a model under the criteria of expectation maximization, utilizing characteristic parameter set of mapping voice of the model and finally achieving a high-quality voice conversion effect. According to the high-quality voice conversion method based on the modeling of the signal timing characteristics, strong correlation between the voice signal parameters is fully utilized, a novel hybrid Kalman filter is constructed by means of a physical process that simulation parameters change with time and is used for a parameter mapping process of the voice conversion, a set of special conversion algorithm which associates the parameter of the Kalman filter with physical properties of a voice signal is designed, and therefore a conversion of personality traits of a speaker can be achieved.

Description

technical field [0001] The present invention relates to speech conversion technology, which is a technology that combines speech recognition and speech synthesis technology to realize the transformation of a speaker's voice so that it sounds like another specific speaker's voice, especially a technology based on signal timing characteristics. Modeled High-Quality Speech Transformation Methods. Background technique [0002] Speech conversion technology is an emerging research branch in the field of speech signal processing in recent years, covering the fields of speech recognition and speech synthesis. A person's voice personality characteristics, so that his (or her) speech is perceived by the listener as the speech of another specific speaker (called the target speaker). The main tasks of speech conversion include extracting characteristic parameters representing the speaker's personality and performing mathematical transformation, and then reconstructing the transformed p...

AI Technical Summary

Problems solved by technology

However, this type of algorithm also has some disadvantages, such as artificially assuming that the data satisfies the condition of independent and identical distribution, and in the process of feature conversion, the forced conversion method is performed in a frame-by-frame order

Although this method of ignoring the inter-frame parameter correlation greatly simplifies the problem and reduces the difficulty of solving it, it violates the fact that there is a strong correlation in the speech signal, which leads to a decline in the ability of the model to describe the time-varying characteristics of the signal, and ultimately affects The effect of voice change

Images