A voice engine parameter configuration method and device

A parameter configuration method and voice engine technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as increased workload, inability to meet the needs of all terminals, and large differences in voice control effects, saving tedious operations Effect

Active Publication Date: 2021-03-16
ZTE CORP
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the different degrees of adaptation between the terminal itself and the voice engine, the effect of voice control will vary greatly. How to adapt the voice engine according to the inherent attributes of the terminal itself, so as to improve the accuracy of voice recognition and the naturalness of voice broadcast, and finally achieve The best voice user experience is meaningful and valuable
[0003] The traditional implementation method is usually to set a series of default optimal parameters for the voice engine to adapt to all terminals, but because the configuration parameters of each terminal are different, this configuration method cannot meet the needs of all terminals; Each terminal re-adjusts the parameters of the speech engine to improve the speech recognition rate and broadcast naturalness on the terminal
However, it is obvious that a set of voice engine parameters is only suitable for one type of terminal, and when it is transplanted to other terminals, it often cannot achieve the best voice experience effect; Increased workload when there is terminal production

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
  • A voice engine parameter configuration method and device
  • A voice engine parameter configuration method and device
  • A voice engine parameter configuration method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiment 1 of the present invention provides a voice engine parameter configuration method, such as figure 1 As shown, the method includes the following steps:

[0043] Step 101: Obtain terminal voice configuration information and identifiable parameter items of the voice engine in the terminal;

[0044]Specifically, the voice configuration information, as the hardware information of the terminal, is usually stored in the terminal in the form of a data table. Therefore, the voice configuration information of the terminal can be obtained by directly looking up the corresponding data table. Usually, the voice configuration information includes: voice configuration information items and voice The information parameters corresponding to the configuration information items; for example, the voice configuration information items may include: whether to support full-duplex, whether there is a recording noise reduction chip, whether to support close-range recording, whether i...

Embodiment 2

[0089] Embodiment 2 of the present invention provides a speech engine parameter configuration device, such as figure 2 As shown, the device includes: a voice configuration information acquisition module 21, an identifiable parameter item acquisition module 22, a first voice parameter item acquisition module 23, a second voice parameter item generation module 24 and a configuration module 25; wherein,

[0090] The voice configuration information acquisition module 21 is used to acquire the voice configuration information of the terminal;

[0091] The identifiable parameter item acquisition module 22 is used to acquire the identifiable parameter item of the speech engine in the terminal;

[0092] The first voice parameter item acquisition module 23 is configured to acquire the first voice parameter item corresponding to the voice configuration information;

[0093] The second speech parameter item generation module 24 is used to generate a second speech parameter item accordin...

Embodiment 3

[0107] Embodiment 5 of the present invention provides a terminal, including the speech engine parameter configuration device provided in Embodiment 2 above.

[0108] In the specific implementation process, the above-mentioned voice configuration information acquisition module 21, identifiable parameter item acquisition module 22, first voice parameter item acquisition module 23, second voice parameter item generation module 24 and configuration module 25 can be processed by the central processing unit in the terminal. CPU (Central Processing Unit), microprocessor (MPU, Micro Processing Unit), digital signal processor (DSP, Digital Signal Processor) or programmable logic array (FPGA, Field-Programmable Gate Array).

[0109] Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, ...

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 voice engine parameter configuration method, which comprises acquiring terminal voice configuration information and identifiable parameter items of the voice engine in the terminal; acquiring the first voice parameter item corresponding to the voice configuration information; according to the first voice parameter item , and the parameter items in the identifiable parameter items of the speech engine generate a second speech parameter item; configure the parameter value of the second speech parameter item according to the optimal parameter setting recommendation table. The invention also discloses a voice engine parameter configuration device.

Description

technical field [0001] The invention relates to the field of mobile communication, in particular to a voice engine parameter configuration method and device. Background technique [0002] With the development of voice technology, voice recognition and voice broadcast have gradually become familiar and frequently used functions for ordinary users. However, due to the different degrees of adaptation between the terminal itself and the voice engine, the effect of voice control will vary greatly. How to adapt the voice engine according to the inherent attributes of the terminal itself, so as to improve the accuracy of voice recognition and the naturalness of voice broadcast, and finally achieve The best voice user experience is meaningful and valuable. [0003] The traditional implementation method is usually to set a series of default optimal parameters for the voice engine to adapt to all terminals, but because the configuration parameters of each terminal are different, this...

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 Patents(China)
IPC IPC(8): G10L15/22G10L15/28H04M1/72433H04M1/725
CPCH04M1/725
Inventor 谢志华
Owner ZTE CORP
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