Speech synthesis method and device, and medium

A speech synthesis and speech technology, applied in the Internet field, can solve the problems of reduced speech synthesis work efficiency, reduced speech synthesis work efficiency, poor speech synthesis effect, etc.

Active Publication Date: 2021-05-28
北京中关村科金技术有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, speech synthesis technology is divided into the following three methods: synthesis based on splicing, end-to-end synthesis, and parameter-based synthesis. The splicing-based method is based on the splicing of individual recording segments, so a relatively comprehensive recording library is required, resulting in the need for The workload of the recorded recording library is heavy, which reduces the work efficiency of speech synthesis; end-to-end synthesis is a deep learning method, which also requires a large number of high-quality recording data samples for model training; although the method based on parameter synthesis does not require a large number of Recording library, you can build a database model based on a small amount of recording data containing key parameters, and then perform speech synthesis, but the speech synthesis result of this method will lead to poor speech synthesis effect
[0003] At present, there is no effective method to improve the quality of speech synthesis while reducing the work efficiency of speech synthesis

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Speech synthesis method and device, and medium
  • Speech synthesis method and device, and medium
  • Speech synthesis method and device, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] According to this embodiment, an embodiment of a speech synthesis method is also provided. It should be noted that the steps shown in the flowcharts of the drawings can be executed in a computer system such as a set of computer-executable instructions, and, although A logical order is shown in the flowcharts, but in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0035] The method embodiments provided in this embodiment can be executed in mobile terminals, computer terminals, servers or similar computing devices. figure 1 A hardware structural block diagram of a computing device for implementing a speech synthesis method is shown. Such as figure 1 As shown, the computing device may include one or more processors (processors may include but not limited to processing devices such as microprocessors MCUs or programmable logic devices FPGAs), memory for storing data, and memory for communication function...

Embodiment 2

[0078] image 3 It is a schematic diagram of a speech synthesis device provided by an embodiment of the present disclosure, and the device 300 corresponds to a speech synthesis method according to Embodiment 1. refer to image 3 As shown, the device 300 includes:

[0079] A target number acquisition module 301, configured to acquire a target number to be synthesized;

[0080] The digital unit determination module 302 is configured to determine two target digital units to be synthesized required for synthesizing the speech of the target number to be synthesized according to preset rules, wherein the two target digital units to be synthesized are divided into The target digital unit to be synthesized at the low position and the target digital unit to be synthesized at the high position;

[0081] The voice sample determination module 303 is used to respectively determine the voice samples corresponding to the target number unit to be synthesized in the pre-recorded digital voi...

Embodiment 3

[0098] Figure 4 It is a schematic diagram of a speech synthesis apparatus provided in another embodiment of the present disclosure, and the apparatus 400 corresponds to the method according to the first aspect of Embodiment 1. refer to Figure 4 As shown, the device 400 includes: a processor 410; and a memory 420, connected to the processor 410, for providing the processor 410 with instructions for processing the following processing steps:

[0099] Determine the two target digital units to be synthesized that are required to synthesize the speech of the target number to be synthesized according to preset rules, wherein the two target digital units to be synthesized are divided into low-order target digital units to be synthesized and high-order according to the number of digits. The target digital unit to be synthesized;

[0100] In the pre-recorded digital voice bank, respectively determine the voice samples corresponding to the target number unit to be synthesized, and i...

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

No PUM Login to view more

Abstract

The invention discloses a speech synthesis method and device, and a storage medium. The method comprises the following steps: obtaining a to-be-synthesized target number, and determining two to-be-synthesized target number units needed for synthesizing the speech of the to-be-synthesized target number according to a preset rule, wherein the two to-be-synthesized target digital units are divided into a low-order to-be-synthesized target digital unit and a high-order to-be-synthesized target digital unit according to digits where the two to-be-synthesized target digital units are located; respectively determining voice samples corresponding to the to-be-synthesized target digital units in a pre-recorded digital voice library; intercepting voice units of to-be-synthesized target digits from the voice samples; and synthesizing the voice of the to-be-synthesized target number by using the voice unit. According to the embodiment of the invention, the working efficiency of speech synthesis and the speech synthesis quality can be improved at the same time.

Description

technical field [0001] The present application relates to the Internet field, in particular to a voice synthesis method, device and medium. Background technique [0002] With the rapid development of Internet technology, speech synthesis technology has sprung up to meet the needs of various industries for intelligent speech. At present, speech synthesis technology is divided into the following three methods: synthesis based on splicing, end-to-end synthesis, and parameter-based synthesis. The splicing-based method is based on the splicing of individual recording segments, so a relatively comprehensive recording library is required, resulting in the need for The workload of the recorded recording library is heavy, which reduces the work efficiency of speech synthesis; end-to-end synthesis is a deep learning method, which also requires a large number of high-quality recording data samples for model training; although the method based on parameter synthesis does not require a l...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L13/02G10L13/06
CPCG10L13/02G10L13/06
Inventor 崔文强杨春勇靳丁南权圣
Owner 北京中关村科金技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap