Morse code deep learning training data manufacturing method

Abstract

The invention relates to the technical field of communication signal processing, in particular to a Morse code deep learning training data manufacturing method. The method comprises the following steps: S1, acquiring a Morse code audio signal sample, and preprocessing the Morse code audio signal sample to obtain a preprocessed audio signal; S2, analyzing and converting the preprocessed audio signal to generate a frequency spectrum picture of the audio signal; S3, establishing a neural network model to perform automatic pre-marking of training data on the spectrum picture; S4, manually markingtraining data of the spectrum picture after automatic pre-marking; and S5, generating a training data marking result by integrating the automatic pre-marking result and the manual marking result, andstoring the training data marking result and the Morse code audio signal sample in an associated manner. According to the method, the production of the Morse code deep learning training data can be completed quickly, efficiently and accurately, and a training data set is provided for the deep learning and intelligent identification of the Morse code.

Description

technical field [0001] The invention relates to the technical field of communication signal processing, in particular to a method for making Morse code deep learning training data. Background technique [0002] Telegraph communication in the world generally adopts the Morse code method, and manual copying is used in the process of copying and receiving messages. There is no machine or equipment that can replace manual copying and receiving of messages. As an international telegraph communication symbol, Morse code uses various combinations of signals of different lengths to represent certain letters, numbers and punctuation marks. When writing, a short signal is generally represented by a dot ".", and a long signal is represented by a dash "-". In order to distinguish dots and dashes and to distinguish each character, there are strict regulations on the length of dots and dashes and various intervals: 1 dash is equal to the length of 3 dots without intervals; in a character...

AI Technical Summary

Problems solved by technology

It can be seen from this that there are three major defects in the manual copying work method: 1. The operator's working hours are short. Generally, the manual operator has to rest after working for two hours, and cannot perform continuous copying work for a long time; 2. The operator The labor intensity is high, and the telegraph operator must have super brain and manual skills, receive and grasp the sound signal very accurately, and correct the few errors in the process of sending the machine to get a text file as the result of the message. ; 3. The operator training period is long, which is not conducive to rapid and large-scale replication

However, training data sets for certain types are scarce, especially in the field of recognizing Morse code sound signals, and there are no public data sets in the world

On the other hand, due to the particularity of the radio Morse code sound signal, such as high noise, only a long-term trained operator can identify the signal in the high noise sound, which also brings great challenges to the establishment of data sets. great difficulty

Images