Speech synthesis method, device, electronic device and storage medium
A technology of speech synthesis and speech features, which is applied in the computer field and can solve the problems of poor speech authenticity and naturalness
Active Publication Date: 2022-06-17
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in the speech synthesis method in the prior art, the authenticity and naturalness of the synthesized speech are poor
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
Embodiment Construction
[0017] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.
[0018] Speech can include speech recognition, speech separation, speech interaction, speech synthesis and other technical fields, and is an important direction in the field of artificial intelligence.
[0019] Speech synthesis (Voice Synthesis) is a technology that allows machines to convert text information into outputable speech, involving fields such as acoustics...
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 present disclosure provides a speech synthesis method, device, electronic equipment, and storage medium, which relate to the technical fields of speech and artificial intelligence, and in particular to the technical fields of speech synthesis, natural language processing, and deep learning. The specific implementation plan is as follows: obtain the text to be synthesized and the speech features of the target user, and obtain the predicted first acoustic feature according to the text to be synthesized and speech features; obtain the target template audio from the template audio library according to the text to be synthesized, extract The second acoustic feature of the target template audio; splicing the first acoustic feature and the second acoustic feature to generate the target acoustic feature; based on the target acoustic feature and the voice feature, performing speech synthesis on the text to be synthesized to generate the target voice. Thus, the target acoustic feature can have the first acoustic feature of the text to be synthesized and the second acoustic feature of the target template audio, and the feature representation effect is better, which helps to improve the authenticity and naturalness of the target speech, and the speech synthesis effect is better. it is good.
Description
technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to a speech synthesis method, apparatus, electronic device, storage medium and computer program product. Background technique [0002] At present, speech synthesis methods can convert text into audio with the characteristics of the target user's voice, and have been widely used in voice chat, smart home and other fields. For example, in a voice chat scenario, after receiving the user's chat voice, the matching chat text can be obtained, and the chat text can be converted into audio with the characteristics of the target user's voice in real time, and the audio can be played or fed back to the user terminal. However, in the speech synthesis method in the prior art, the authenticity and naturalness of the synthesized speech are poor. SUMMARY OF THE INVENTION [0003] The present disclosure provides a speech synthesis method, apparatus, electronic device, storage med...
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 Patents(China)
IPC IPC(8): G10L13/047G10L13/04G10L13/08G10L25/30G06N3/04G06N3/08
CPCG10L13/047G10L13/04G10L13/08G10L25/30G06N3/04G06N3/08G10L13/06G06N3/0464G10L15/02
Inventor 高正坤张君腾孙涛贾磊
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD