A terminal voice broadcast method, device and terminal voice operation method

A voice broadcast and voice technology, applied in the fields of devices, terminal voice operations, and terminal voice broadcast methods, can solve problems such as the final recognition result does not match the user, wrong commands are executed, etc.

Active Publication Date: 2016-09-28
NUBIA TECHNOLOGY CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the user's verbal mistakes or the recognition rate of the speech recognition system, it is inevitable that the final recognition result does not meet the user's intention. Causes the wrong command to be executed

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 terminal voice broadcast method, device and terminal voice operation method
  • A terminal voice broadcast method, device and terminal voice operation method
  • A terminal voice broadcast method, device and terminal voice operation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] The embodiment of the present invention solves the defect in the prior art that wrong commands are executed due to voice recognition errors by providing a voice broadcast method and device, and the method can be applied in voice input methods, voice navigation, robot voice dialogue, etc. Used in scenarios, the terminal can correct the voice information being broadcast, effectively reflecting the role of human-computer interaction and improving user experience.

[0092] see image 3 , image 3 A flow chart of a method according to an embodiment of the present invention is shown, including the following steps:

[0093] Step S101, the terminal receives a first voice signal through a microphone.

[0094] In one embodiment, before acquiring the voice data input by the user, the user first activates the voice recognition system by means of a terminal physical button or a touch on the screen. After starting the voice recognition system, the terminal receives a first voice s...

Embodiment 2

[0118] The invention provides a terminal voice broadcast method, Figure 5 It shows the flow chart of the method of the embodiment of the present invention. The difference from Embodiment 1 is that it also includes a method for correcting the misrecognized character string in the first speech recognition result. Only the different steps will be described below. The same The steps are not repeated here. Include the following steps:

[0119] Step S304, when the terminal receives the error-correcting voice signal input by the user, it pauses the voice broadcast, and saves the first voice recognition result in the form of a character string.

[0120] In one embodiment, the first voice signal input by the user is converted into a character string, so as to process the first voice signal.

[0121] Step S305 , recognizing the error-corrected speech, and determining an incorrectly recognized speech character string in the first speech recognition result according to the error-correc...

Embodiment 3

[0131] The present invention provides a terminal voice operation method, Figure 6 A flow chart of a method according to an embodiment of the present invention is shown, including the following steps:

[0132] In step S501, a microphone receives a first voice instruction.

[0133] In one embodiment, after the voice recognition system is activated by the terminal, the microphone receives the first voice command, and the first voice command is a voice command generated when the user inputs a voice signal.

[0134] In one embodiment, before obtaining the voice data input by the user, the user first activates the voice recognition system by means of a terminal physical button or a touch on the screen, and the voice recognition system responds to the user's voice input, that is, receives the voice signal input by the user.

[0135] Step S502, recognizing the first voice instruction, and saving the recognition result of the first voice instruction.

[0136] In one embodiment, the ...

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 terminal voice broadcast method, device and terminal voice operation method. The terminal voice broadcast method includes the steps of: the terminal receives a first voice signal through a microphone; performs voice recognition to obtain the first voice recognition result, and broadcasts the first voice recognition result. Describe the first voice recognition result; in the voice broadcast process, detect whether the microphone receives the error correction voice signal input by the user, if the error correction voice signal is received, then suspend the voice broadcast; recognize the error correction voice signal, and obtain producing error-corrected speech recognition results; using the error-corrected speech to replace misrecognized speech, and generating a second speech recognition result after correction; broadcasting the second speech recognition result. In the process of voice broadcast, for the wrong voice recognition generated, the user can interrupt the voice broadcast by inputting the error-correcting voice, and continue the voice broadcast after correcting the voice recognition result according to the error-correcting voice, thereby avoiding errors caused by voice recognition errors. Wrong command was executed.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, and more specifically, to a terminal voice broadcast method and device, and a terminal voice operation method. Background technique [0002] The traditional speech recognition system wakes up by keystrokes, keywords, etc., then records a sound, sends the recorded audio file to the cloud or local speech recognition engine, recognizes and interprets it, and finally the terminal broadcasts the speech recognition result and performs corresponding operations , so as to achieve the purpose of controlling the terminal by voice. However, due to the user's verbal mistakes or the recognition rate of the speech recognition system, it is inevitable that the final recognition result does not meet the user's intention. Causes the wrong command to be executed. For example, "Call Li Yang" is recognized as "Call Lin Yang". If there is "Lin Yang" in the address book, you may directly call "Lin ...

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): G10L15/00G10L15/26H04M1/725H04M1/72433H04M1/72454
Inventor 秦永利
Owner NUBIA TECHNOLOGY 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