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

Voice recognition method and device

A technology of speech recognition and speech information, applied in speech recognition, speech analysis, special data processing applications, etc., can solve the problems of speech recognition system, such as slow speech recognition speed, large text library, inconvenient maintenance, etc., to improve speed, The effect of reducing scale and improving accuracy

Active Publication Date: 2012-10-24
成都车音智能科技有限公司
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to improve the success rate and accuracy of speech recognition, it is necessary to store all expressions of different things in the text library of the speech recognition system as much as possible, which makes the text library of the speech recognition system very large in scale and inconvenient to maintain; and Due to the large size of the text library, the speech recognition system is slow to perform speech recognition

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
  • Voice recognition method and device
  • Voice recognition method and device
  • Voice recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, the speech recognition method provided by the embodiment of the present invention includes:

[0048] In step 101, text information corresponding to voice information input by a user is acquired.

[0049] In order to make the voice recognition method provided by the embodiment of the present invention have a wider scope of application, and to be able to recognize voice information of users in different regions and with different accents, in this embodiment, step 101 can use non-specific voice recognition technology to analyze the voice input by the user. The information is identified and analyzed, and the text information corresponding to the voice information is obtained.

[0050] Step 102, using the preset target information database and load library to perform word segmentation processing on the text information, and obtain target information corresponding to the target information database.

[0051] In this embodiment, the target informat...

Embodiment 2

[0058] Such as figure 2 As shown, the speech recognition method provided by the embodiment of the present invention includes:

[0059] Step 201, obtain the text information corresponding to the voice information input by the user; the specific information is related to figure 1 The shown step 101 is similar and will not be repeated here.

[0060] Step 202, matching the text information with the information contained in the target information database and the load library respectively.

[0061] In this embodiment, step 202 can match the words in the text information with the information contained in the target information database and the load library according to the sequence; or match the words in the text information with the The target information database and the information contained in the load library are matched; the information contained in the target information database and the load library can also be matched in other ways, which will not be repeated here. Opti...

Embodiment 3

[0076] Such as image 3 As shown, the speech recognition method provided by the embodiment of the present invention includes:

[0077] From step 301 to step 302, the words contained in the text information corresponding to the voice information are obtained, and the corresponding target information is obtained; the specific process is the same as figure 1 Steps 101 to 102 shown are similar and will not be repeated here.

[0078] Step 303, if at least two pieces of target information are acquired, connective words between the target information are acquired.

[0079] Step 304, determine the content of the voice information according to the target information and connecting words.

[0080] Optionally, in order to make the speech recognition method provided by the embodiment of the present invention applicable to multiple fields such as navigation, audio-visual entertainment fields, etc., the target information database and load library can be set to a broad range; preferably, ...

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 recognition method and device, and relates to the field of voice recognition, and the method and the device are used for solving the problem that the existing voice recognition technology is slow in recognition speed. The technical scheme provided by the invention is as follows: the method comprise the following steps of: acquiring literal information corresponding to voice information input by users; performing word segmentation processing on the literal information through a preset target information data base and a load library, acquiring target information corresponding to the target information data base, wherein the target information data base is used for storing information to be subjected to voice recognition, and the load library is used for storing information except for words with essential meaning; and determining the content of the voice information according to the target information. The voice recognition method and device provided by the embodiment of the invention can be applied to systems for information service such as navigation, jukeboxes and, contact inquiry.

Description

technical field [0001] The invention relates to speech recognition technology, in particular to a speech recognition method and device. Background technique [0002] With the continuous development of computer and information technology, voice interaction has become a necessary means of human-computer interaction. As one of the important technologies of voice interaction, after nearly half a century of development, voice recognition technology has become increasingly mature and widely used. [0003] Due to the large number of Chinese characters and vocabulary, in order to improve the accuracy of the Chinese speech recognition system, the traditional speech recognition system needs to compare the speech content sent by the user from the beginning to the end with the pre-stored text content in the text library Match one by one. Only when the voice content completely matches a certain text content stored in the text library, the voice recognition system can recognize the meani...

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): G10L15/26G10L15/00G06F17/30
Inventor 王力劭许军庞泽耀邵颖王钢
Owner 成都车音智能科技有限公司