Virtual human animation synthesis method and system based on global emotion coding

Abstract

The invention provides a virtual human animation synthesis method and system based on global emotion coding. The method comprises steps of converting an input voice feature into a phoneme posterior probability feature through employing a voice recognition model, obtaining a simulation noise sequence through employing a noise encoder, carrying out the summation of the simulation noise sequence and the phoneme posterior probability feature, obtaining phoneme posterior probability features with noise, and obtaining global content features through a full connection layer; extracting a Mel-frequency cepstrum coefficient feature sequence for emotional voice, extracting a global acoustic feature vector through a bidirectional gating loop unit network, setting an implicit vector matrix, and carrying out attention calculation on the global acoustic feature vector and the implicit vector to obtain a global emotional feature. The method is advantaged in that the global emotion features are spliced to the global content features, the context information is modeled through a bidirectional long-short-term memory network, face animation parameters corresponding to emotion and mouth shape information are generated, and finally virtual human animation with emotion is generated.

Description

technical field [0001] The invention relates to the field of speech processing, in particular to a virtual human animation synthesis method and system based on global emotion coding. Background technique [0002] At present, voice-driven virtual human animation generation has received a lot of research in the industry, and its practical value has been proved by a large number of landing application scenarios. The traditional voice-driven virtual human animation generation mainly focuses on the generated mouth shape effect, and pays less attention to the expression and emotion of the generated face. Emotional expressive virtual human animation generation is also widely used in actual scenes. On the one hand, emotional expressiveness can enhance the authenticity of virtual images, improve user interaction experience, and enhance user interaction willingness. In products such as assistants and virtual companions, compared with the original traditional method, it brings users a...

AI Technical Summary

Problems solved by technology

[0011] In order to solve the technical problems of insufficient control effect of animation emotion generation, inability to automatically extract input voice emotion and generate emotion control, and inability to realize anti-noise of virtual human animation generation system, the present invention proposes a virtual human animation synthesis based on global emotion coding method and system

Images