Speech synthesis method and device

A speech synthesis and speech technology, applied in the field of data processing, can solve the problems of difficult popularization and high cost

Active Publication Date: 2018-08-03
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this traditional method works well, it requires a large amount of corpus to be pre-recorded for each tone, and separate training models are required for different tones, which is costly and difficult to popularize.

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
  • Speech synthesis method and device
  • Speech synthesis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0072] The data processing device belongs to a kind of intelligent device with data processing function. In the scene where the data processing device interacts with the user, the data processing device needs to synthesize voice playback according to the scene or the content of the dialogue to complete the interaction with the user. The speech synthesized by the processing device does not have tone components, which will make the interactor (user) feel cold, resulting in a poor interactive user experience. Therefore, in order to improve the user experience, it is necessary to add tone to the synthesized speech, so that the synthesized speech can be closer to the voice of a normal person, so as to achieve the effect of improving the user experience in the interaction.

[0073] In the traditional way, for a language segment, if you want to synthesize speech with a...

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

An embodiment of the invention discloses a speech synthesis method and a speech synthesis device. When acquiring a speech synthesis request, corresponding neutral speech acoustic parameters can be determined according to at least one semantic unit contained in a language segment of a speech to be synthesized and by means of a statistical model established based on neutral speech acoustic parameters, and the determined neutral speech acoustic parameters are processed correspondingly according to mood characteristics of a specific mood to obtain a specific mood segment in the specific mood. Therefore, the speech synthesis method and the speech synthesis device can synthesize the specific mood segment according to the statistical model established based on the neutral speech acoustic parameters and the mood characteristics without recording speeches in a large amount of specific moods in advance, thus the cost of speech synthesis is reduced; and the speech segment in the required mood canbe synthesized for any mood by adopting the statistical model and the corresponding mood characteristics, thereby greatly enlarging the application range of the speech synthesis scheme.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a speech synthesis method and device. Background technique [0002] With the development of computer technology, many interactive scenarios require data processing equipment to directly or indirectly perform voice interaction with users, such as voice prompts in electronic navigation, rush answers and voice answers in robot answering sessions, etc. [0003] Since the voices emitted by the machine are basically synthesized by the machine and used to simulate human language, the pronunciation of this type of voice is cold and has no emotional color, so this type of voice does not bring users a good feeling. In order to improve the user experience during the interaction process, the voice produced by the machine needs to reflect the proper tone according to the context. [0004] The traditional method is to collect a large amount of corpus with this tone in advance for a certain tone...

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): G10L13/02G10L13/10G10L15/14
CPCG10L13/02G10L13/10G10L15/144
Inventor 孟凡博
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
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