Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chinese civil aviation air traffic control speech recognition method and system

A technology of air traffic control and voice recognition, which is applied in traffic control systems, voice recognition, aircraft traffic control, etc., can solve the problems that the recognition accuracy needs to be improved, and achieve the effect of high recognition accuracy

Pending Publication Date: 2021-07-23
XIAMEN UNIV
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing speech recognition technology used in the field of speech recognition for traffic control in Chinese civil aviation is mainly based on the "CLDNN" neural network based on deep learning, which consists of multi-layer CNN, multi-layer LSTM, and multi-layer fully connected neural network. However, the existing technical solutions The recognition accuracy still needs to be improved

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
  • Chinese civil aviation air traffic control speech recognition method and system
  • Chinese civil aviation air traffic control speech recognition method and system
  • Chinese civil aviation air traffic control speech recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , the present embodiment provides a method for voice recognition of traffic control in Chinese civil aviation, the method comprising the following steps:

[0044] Step 101: Acquiring voice feature data, which is time-series feature information extracted based on the voice signal;

[0045] Step 102: Input the speech feature data into the trained acoustic model to obtain a recognition result, the recognition result represents the Chinese term for air traffic control corresponding to the speech signal; the acoustic model includes: sequentially connected TRM modules, BiGRU module, fully connected layer FC and CTC module, the TRM module includes sequentially connected multi-head self-attention layer, the first residual connection and layer normalization layer, feed-forward layer and the second residual connection and layer normalization layer, so The BiGRU module includes a two-way gated recurrent unit network, the CTC module includes a connection time-series c...

Embodiment 2

[0080] see Figure 9 , the present embodiment provides a Chinese civil aviation traffic control voice recognition system, the system includes:

[0081]The voice feature data acquisition module 901 is used to acquire the voice feature data, the voice feature data is time-series feature information extracted based on the voice signal;

[0082] Speech recognition module 902, is used for inputting described speech feature data into the acoustic model through training, obtains recognition result, and described recognition result represents the air traffic control Chinese term text corresponding to described speech signal; Described acoustic model comprises: The TRM module, BiGRU module, fully connected layer FC and CTC module, the TRM module includes sequentially connected multi-head self-attention layer, the first residual connection and layer normalization layer, feed-forward layer and the second residual connection and layer In the standardization layer, the BiGRU module includ...

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 Chinese civil aviation air traffic control speech recognition method and system. The method comprises the following steps: acquiring voice feature data, wherein the voice feature data is time sequence feature information extracted based on a voice signal; and inputting the voice feature data into a trained acoustic model to obtain a recognition result which represents air traffic control Chinese term characters corresponding to the voice signal; wherein the acoustic model comprises a TRM module, a BiGRU module, a full connection layer and a CTC module which are connected in sequence, the TRM module comprises a multi-head self-attention layer, a first residual connection and layer standardization layer, a feed-forward layer and a second residual connection and layer standardization layer which are connected in sequence, the BiGRU module comprises a bidirectional gating circulation unit network, the CTC module comprises a connection time sequence classification layer, and the acoustic model is obtained by training an air traffic control instruction term voice sample with a Chinese character label. The method has the advantage of high recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a voice recognition method and system for traffic control in Chinese civil aviation. Background technique [0002] Air traffic control mainly conducts command and dispatch of aircraft taxiing on the ground and flight routes, which is an important guarantee for the safety and efficiency of air traffic, and it is extremely dependent on air traffic control personnel. The land-to-air conversation between air traffic controllers and crew is closely related to flight safety, so it is necessary to convert the land-to-air conversation into a text record and archive it. [0003] The existing speech recognition technology used in the field of speech recognition for traffic control in Chinese civil aviation is mainly based on the "CLDNN" neural network based on deep learning, which consists of multi-layer CNN, multi-layer LSTM, and multi-layer fully connected neural network. Howev...

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): G10L15/02G10L15/26G10L15/16G10L15/06G10L25/24G08G5/00G06N3/04G06N3/08
CPCG10L15/02G10L15/16G10L15/063G10L25/24G08G5/0095G06N3/084G10L2015/0631G06N3/044G06N3/045
Inventor 罗林开俞涵张松飞彭洪黄俊祥江居旺
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com