Voice synthesis broadcasting method and device
A technology of speech synthesis and speech files, which is applied in the field of speech recognition, can solve problems such as single synthesized voice, weak user experience, and unobvious rhythm and rhythm, and achieve reasonable and natural pauses and improve the effect of experience
Inactive Publication Date: 2021-05-14
成都启英泰伦科技有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] 1. Synthesized audio, the naturalness of the broadcast is low, and the rhythm is not obvious;
[0006] 2. The synthesized sound is relatively single, and the user experience is not strong;
[0007] 3. Speech synthesis, by accessing the server, when the traffic is too large or the network is not smooth, it is difficult to meet the needs of customers for rapid synthesis and broadcasting
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
[0044] Specific embodiments of the present invention will be further described in detail below.
[0045] Speech synthesis broadcasting method described in the present invention, as figure 1 shown, including the following steps:
[0046] S1. Process the text to be synthesized to obtain the language features corresponding to the text;
[0047] Wherein, the text processing is usually to unify the language of the text to be synthesized, taking the text to be combined as the main body in Chinese as an example, including the following steps:
[0048] S11. Treat the synthesized text and filter out the special symbols in it. Such as punctuation marks, brackets and other symbols that do not need to be pronounced in the text;
[0049] S12. Perform Arabic numeral processing, diacritic processing, and English character processing on the text to be synthesized;
[0050] When the text contains Arabic numerals, perform digital conversion, such as converting 1 to 9 into corresponding Chin...
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 discloses a voice synthesis broadcasting method and device. The method comprises the following steps: S1, carrying out the text processing of a to-be-synthesized text, and obtaining the language features corresponding to the text; S2, calling a stored neural network model, and predicting acoustic parameters corresponding to the text information according to the neural network model; S3, performing voice synthesis on the acoustic parameters, and outputting a synthesized voice file; and S4, playing the synthesized audio file. According to the voice synthesis broadcasting method, the to-be-synthesized text is processed, acoustic model prediction and voice synthesis are carried out, the broadcasting voice has the effects of high naturalness, clearness, reasonable and natural pause, different timbres and the like, and the user experience is greatly improved.
Description
technical field [0001] The invention belongs to the technical field of speech recognition, relates to speech synthesis technology, in particular to a speech synthesis broadcasting method and device. Background technique [0002] Speech synthesis technology, also known as text-to-speech technology (Text To Speech, TTS), its goal is to allow machines to convert text information into voice output through recognition and understanding, so that machines can speak, which is the future of human-computer interaction. important branch. [0003] Speech synthesis technology is widely used, such as web page content reading, novel audio reading, e-mail reading, car voice navigation broadcast, smart home product broadcast, etc. Taking voice navigation as an example, through voice synthesis, user terminals such as mobile phones and tablet computers can broadcast the driving route required by the user in real time, which brings great convenience to the user. [0004] During the research a...
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): G10L13/04G10L13/02G10L13/08G10L13/10G06N3/08G06N3/04
CPCG10L13/08G10L13/10G10L13/02G06N3/08G10L2013/083G06N3/045
Inventor 潘帅嘉许兵
Owner 成都启英泰伦科技有限公司