The computer then applies a training algorithm to this dataset that eventually discovers the correct "program" - the ML model that provides the best matching function that can infer the correct output, given the input data. As a ML engineer you need to curate a dataset that has a representative selection of input data with corresponding output data (also known as label data). From Morse decoder perspective this is how most decoders work: they take input audio data that contains the Morse signals and after many complex operations the correct decoded text appears on the screen.
#Best morse decoder software
Depending on the complexity of the problem software developer may need to spend quite a long time coming up with the correct algorithms to produce the right output data. In traditional programming we look at the input data and try to write a program that uses some processing steps to come up with the output data. From software development perspective ML is changing the paradigm how we are processing data. I have been quite interested in Machine Learning (ML) technologies for a while. In ham radio terms the difference of 47 dB corresponds roughly eight S units - human ears & brain can still decode S2 level signals whereas conventional software based Morse decoders produce mostly gibberish.
#Best morse decoder code
Humans can still hear and even recognize the Morse code faintly in the noise. Computers equipped with these simplistic models have great difficulties decoding anything meaningful out of this signal. below shows "Hello World" with 35 dB signal-to-noise ratio that most conventional decoders don't have any problems decoding.įigure 2 below shows the same "Hello World" but with -12 dB signal-to-noise ratio using exactly same process as above to extract the demodulated envelope. When the audio signal is noise free and there is no interference, these simplistic methods work fairly well and produce nearly error free decoding. The author has written many different software decoder implementations that use simplistic models to convert a sequence of "Dits" and "Dahs" to corresponding text. I trained a Tensorflow based CNN-LSTM-CTC model with 5.2 hours of Morse audio training set (5000 files) and achieved character error rate of 0.1% and word accuracy of 99.5% I tested the model with audio files containing various levels of noise and found the model to decode relatively accurately down to -3 dB SNR level.ĭecoding Morse code from audio signals is not a novel idea.
0 kommentar(er)
