Audio synthesis method and device, electronic equipment and storage medium
A synthesis method and audio technology, applied in the computer field, can solve the problems of poor audio synthesis flexibility and inability to apply pitch accuracy, etc., to achieve the effect of ensuring pitch accuracy and improving flexibility
Pending Publication Date: 2022-07-01
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The present disclosure provides an audio synthesis method, device, electronic equipment and storage medium to at least solve the problem of poor audio synthesis flexibility in the related art and cannot be applied to audio synthesis scenarios with limited pitch accuracy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
preparation example Construction
[0099] figure 2 is a flow chart of an audio synthesis method according to an exemplary embodiment, such as figure 2 As shown, the audio synthesis method is applied to electronic equipment for description, including the following steps.
[0100] In step S210, the fundamental frequency to be synthesized and the text to be synthesized are obtained.
[0101] The text to be synthesized may be lyric text, and the base frequency to be synthesized is a base frequency sequence used for synthesizing the target synthesized audio.
[0102] In step S220, the text to be synthesized is input into a pre-trained spectral prediction model to obtain spectral envelope information.
[0103] Among them, the spectral prediction model can be a CBHG (Convolution Bank+Highway network+bidirectionalGated Recurrent Unit, convolutional layer+high-speed network+bidirectional recurrent neural network) model, that is, the spectral prediction model consists of a 1-D convolution filter, a high-speed network...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to an audio synthesis method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-synthesized fundamental frequency and a to-be-synthesized text; inputting the text to be synthesized into a pre-trained spectrum prediction model to obtain spectrum envelope information; inputting the spectrum envelope information and the fundamental frequency to be synthesized into a pre-trained Mel spectrum prediction model to obtain a predicted Mel spectrum; and obtaining a target synthetic audio according to the predicted Mel spectrum. According to the method, the to-be-synthesized fundamental frequency is separated from the spectrum envelope, so that the predicted Mel frequency spectrum is adjusted by accurately controlling the to-be-synthesized fundamental frequency when the Mel frequency spectrum is predicted, the purpose of accurately controlling the synthesized audio frequency is finally achieved, the pitch accuracy of the synthesized audio frequency is ensured, the flexibility of audio frequency synthesis is greatly improved, and the user experience is improved. And the method is very suitable for audio synthesis scenes with limitation on pitch accuracy, such as singing synthesis.
Description
technical field [0001] The present disclosure relates to the field of computer technologies, and in particular, to an audio synthesis method, apparatus, electronic device, and storage medium. Background technique [0002] Audio synthesis technology can convert textual information into fluent speech output. In the process of implementing audio synthesis in the related art, synthesized audio is obtained by directly mapping the text to be synthesized to the Mel spectrum. Using this audio synthesis method, the pitch accuracy of the synthesized audio cannot be adjusted, and the flexibility of audio synthesis is poor. Suitable for audio synthesis scenarios where pitch accuracy is limited, such as singing synthesis. SUMMARY OF THE INVENTION [0003] The present disclosure provides an audio synthesis method, device, electronic device and storage medium to at least solve the problem of poor flexibility of audio synthesis in the related art, which cannot be applied to audio synthes...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G10L13/027G10L25/24G10L25/30
CPCG10L13/027G10L25/24G10L25/30
Inventor 肖金霸王晓瑞
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD