Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech recognition method and device

A technology of speech recognition and speech library, applied in the field of electronic information, can solve the problems of recognition accuracy interference, inability to use voice assistants, inability to recognize voice data, etc.

Inactive Publication Date: 2014-01-01
LE SHI ZHI ZIN ELECTRONIC TECHNOLOGY (TIANJIN) LTD
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, on some smart terminals that support voice technology, the voice data input by the user is only recognized through the online recognition technology of the network, but because the network voice database for online recognition is relatively large, the accuracy of recognition will be disturbed; On the other hand, if the smart terminal does not have a network, the voice assistant cannot be used, which makes it impossible to recognize the voice data input by the user.

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 recognition method and device
  • Speech recognition method and device
  • Speech recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] An embodiment of the present invention provides a voice recognition method, specifically as figure 1 As shown, the method includes:

[0054] 101. The voice recognition device acquires voice data input by a user.

[0055] Specifically, when the voice recognition device performs voice recognition, it will obtain the voice data input by the user. The voice data may be an instruction, such as "shut down", "open the browser", etc., which will not be described in detail in this embodiment of the present invention. limited.

[0056]It should be noted that the speech recognition device is included in a smart terminal, which may be a TV or a pad, which is not specifically limited in this embodiment of the present invention.

[0057] 102. The voice recognition device determines whether voice data can be recognized through a pre-stored local voice database.

[0058] Specifically, after acquiring the voice data input by the user, the voice recognition device first determines whe...

Embodiment 2

[0071] An embodiment of the present invention provides a voice recognition method, specifically as figure 2 As shown, the method includes:

[0072] 201. The voice recognition device acquires voice data input by a user.

[0073] Specifically, when the voice recognition device performs voice recognition, it will obtain the voice data input by the user. The voice data may be an instruction, such as "shut down", "open the browser", etc., which will not be described in detail in this embodiment of the present invention. limited.

[0074] It should be noted that the speech recognition device is included in a smart terminal, which may be a TV or a pad, which is not specifically limited in this embodiment of the present invention.

[0075] 202. The speech recognition device matches the speech data with the speech data in the local speech database to obtain a first matching value.

[0076] Specifically, after the speech recognition device acquires the speech data input by the user,...

Embodiment 3

[0125] An embodiment of the present invention provides a speech recognition device 400, specifically as Figure 4 As shown, the apparatus 400 includes an acquisition unit 401 , a determination unit 402 , and an identification unit 403 .

[0126] The acquiring unit 401 is configured to acquire voice data input by a user.

[0127] The determining unit 402 is configured to determine whether the voice data acquired by the acquiring unit 401 can be recognized through the pre-stored local voice library.

[0128] The recognition unit 403 is configured to recognize the voice data according to the pre-stored local voice database if it is determined that the voice data can be recognized through the pre-stored local voice database.

[0129] Further, the identification unit 403 is also used for:

[0130] After the determining unit 402 determines whether the voice data can be recognized through the pre-stored local voice database, if it is determined that the voice data cannot be recogni...

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 provides a speech recognition method and device. The speech recognition method and device can be used for recognizing speech data inputted by a user without a network and recognition results are more accurate. The method comprises the steps of obtaining the speech data inputted by the user, determining whether the speech data can be recognized through a prestored local speech database, and recognizing the speech data according to the prestored local speech database if the speech data can be recognized through the prestored local speech database. The speech recognition method and device is applicable to the field of the electronic information technology.

Description

technical field [0001] The invention relates to the technical field of electronic information, in particular to a voice recognition method and device. Background technique [0002] With the improvement of people's living standards, the popularity of smart terminals is getting higher and higher. Input methods of smart terminals include user manual input and voice input, wherein voice input has been increasingly applied to today's smart terminals. [0003] In the field of voice input, voice recognition is particularly important. Accurate recognition of commonly used commands can provide better data for later semantic analysis, so as to ensure a better understanding of the user's true intentions through voice assistants. [0004] In the prior art, on some smart terminals that support voice technology, the voice data input by the user is only recognized through the online recognition technology of the network, but because the network voice database for online recognition is rel...

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
IPC IPC(8): G10L15/00
Inventor 初超田甲子黄滔仝永辉
Owner LE SHI ZHI ZIN ELECTRONIC TECHNOLOGY (TIANJIN) LTD