English speech synthesis method and system, electronic equipment and storage medium
A synthesis method, English technology, applied in the field of English speech synthesis, can solve problems such as insufficient clarity, naturalness, and large information loss, and achieve the effect of ensuring quality and real-time performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] This embodiment provides a method for synthesizing English speech, such as figure 1 shown, including the following steps:
[0046] Step S101, converting the target English text into a corresponding text vector.
[0047] In an optional implementation manner, before step S101, preprocessing the target English text is also included. In one example, regularization processing is performed on the target English text, such as removing garbled characters or non-standard symbols in the target English text. In another example, Chinese symbols in the target English text are replaced with corresponding English symbols. In another example, the numbers in the target English text are converted into English words in the corresponding scene. For example, for the same number "205", if the corresponding scene is a room number, the corresponding English words are "two, zero, five"; if the corresponding scene is money, the corresponding English words are "two hundred and five ".
[004...
Embodiment 2
[0066] The present embodiment provides a kind of synthesis system 40 of English speech, as Figure 4 As shown, it includes a text processing module 41 , a feature extraction module 42 , a prediction module 43 and a vocoder 44 .
[0067] The text processing module 41 is used to convert the target English text into corresponding text vectors.
[0068] In an optional implementation manner, the text processing module 41 is also used to preprocess the target English text. In one example, regularization is performed on the target English text. In another example, Chinese symbols in the target English text are replaced with corresponding English symbols. In another example, the numbers in the target English text are converted into English words in the corresponding scene.
[0069] The feature extraction module 42 is used to extract the parameters of the template audio corresponding to the target sentence pattern, and convert the parameters into corresponding parameter vectors; whe...
Embodiment 3
[0077] Figure 5 A schematic structural diagram of an electronic device provided in this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor implements the English speech synthesis method in Embodiment 1 when executing the program. Figure 5 The electronic device 3 shown is only an example, and should not impose any limitation on the functions and application scope of the embodiments of the present invention.
[0078] The electronic device 3 may be in the form of a general computing device, eg it may be a server device. Components of the electronic device 3 may include but not limited to: the at least one processor 4 mentioned above, the at least one memory 5 mentioned above, and the bus 6 connecting different system components (including the memory 5 and the processor 4 ).
[0079] The bus 6 includes a data bus, an address bus and a control bus.
[0080] The memory 5 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More