Speech recognition device and speech recognition method

A speech recognition and speech technology, applied in speech recognition, speech analysis, special data processing applications, etc., can solve the problem of spending a lot of time, and achieve the effect of reducing time

Active Publication Date: 2017-01-04
FU TAI HUA IND SHENZHEN +1
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the amount of voice data in the database is relatively large, it takes a lot of time to perform a voice training

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Please refer to figure 1 , is an application structure diagram of a preferred embodiment of the speech recognition device 1 of the present invention. The voice recognition device 1 is used for performing voice training and voice recognition, wherein the voice recognition is to identify the identity of the speaker of the voice. In this embodiment, the speech recognition device 1 can be an electronic device with speech input and speech processing functions such as a personal computer, a smart phone, a robot or a cloud server, and the speech recognition device 1 can perform speech on the input speech in the device. training or speech recognition. In one embodiment, the speech recognition device 1 can also be connected to a cloud server through the Internet or a local area network, and perform speech training or speech recognition in the cloud server. In another embodiment, the speech recognition device 1 can also be connected to the cloud server through the Internet or a...

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 device and a speech recognition method. The speech recognition device comprises a storage unit and a processing unit. The storage unit is used for storing a first database and a second database. The first database is used for storing a preset number of sections of speeches, a characteristic value of every section of speech, and speech characteristic mean value of various users. The second database is used for storing historical speech data. The processing unit comprises a first training module, a transfer module, and a second training module. When a section of speech is newly stored in the first database, the speech training of all of the speeches including the newly stored section of speech is carried out. When the speech training of all of the speeches is finished, the earliest stored section of speech in the first database is transferred to the second database for storage. When the earliest stored section of speech in the first database is transferred to the second database for the storage, the speech training of all of the speeches in the second database is carried out. The speech training is carried out in the first database having a small data size, and therefore the time consumption of the speech training is reduced.

Description

technical field [0001] The invention relates to a speech recognition device and method. Background technique [0002] In the existing technology for identifying voice speakers, a database for storing the speaker template voice and the corresponding voice feature values ​​is usually established, so that the speaker can be identified by comparing the feature values ​​of the speaker voice with the feature values ​​of the template voice identity of. Whenever the user inputs a new template speech, speech training generally needs to be performed in the database, and the speech and speech feature values ​​are stored in the database. However, when the amount of speech data in the database is relatively large, it takes a lot of time to perform a speech training. Contents of the invention [0003] In view of this, it is necessary to provide a speech recognition device and method to solve the above technical problems. [0004] The present invention provides a speech recognition de...

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 Applications(China)
IPC IPC(8): G10L15/06G06F17/30
Inventor 林海兴
Owner FU TAI HUA IND SHENZHEN
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