Prompt tone generating method and device and mobile terminal
A technology of prompt tone and prompt information, applied in speech synthesis, speech analysis, speech recognition, etc., can solve the problems of limited application scope, troublesome, low efficiency, etc., and achieve the effect of simple and convenient implementation, wide application range and strong flexibility
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0072] Embodiment 1 of the present invention provides a method for generating a prompt sound, which realizes generation of prompt sounds based on speech synthesis. The process is as follows figure 1 shown, including the following steps:
[0073] Step S101: Obtain the original prompt information to be played in the application program.
[0074] Wherein, the original prompt information includes at least one of text original prompt information and audio original prompt information.
[0075] For the sound in various applications in the mobile terminal, in addition to the built-in applications of the terminal, there may also be third-party applications, such as map software, etc., which may involve text broadcasts. The text broadcasts that come with the software may be The default voice may also be a text message. Get the default voice or text information as the original prompt information to be played.
[0076] Step S102: Extract text information corresponding to the acquired o...
Embodiment 2
[0089] Embodiment 2 of the present invention provides the implementation process of generating the global voice library in the above-mentioned prompt tone generation method, and its flow is as follows figure 2 shown, including the following steps:
[0090] Step S201: Obtain the input voice of the simulated user, and extract the speech features of the input voice.
[0091] Obtaining the input voice of the simulated user specifically includes: starting the recording function, recording the voice of the simulated user as the input voice of the simulated user; and / or obtaining the voice of the simulated user from other applications as the input voice of the simulated user.
[0092] There are many ways to input the user's voice, such as direct recording, obtaining from other applications, such as voices in social software, voices in call records, etc., and storing these voices. When collecting, each user is taken as a collection object, and all relevant sounds are extracted to fo...
Embodiment 3
[0100] Embodiment 2 of the present invention provides a specific implementation process of the above prompt tone generation method, the principle of which is as follows image 3 shown.
[0101] The speech synthesis method in the present invention can solve problems such as input / use troubles in certain voice usage scenarios, such as between parents and children, between lovers, and so on. It can be realized that the prompt tone of the application software in the terminal is broadcasted by the voice of the children and lovers.
[0102] Such as image 3 As shown, the voices of children, couples, etc. that can simulate users are collected. Taking input voice as an example, after inputting these voices that can simulate users, feature extraction is performed, and a voice library is synthesized based on feature information. The voice library contains various texts / languages Pronunciation is no longer limited to the original voice content. For example, based on a few words spoken...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com