0
$\begingroup$

In ham radio, Morse code is used in CW transmissions (yes even today).

My project is to take already decoded Morse code text strings from an existing decoder and then recognize different conversations (QSOs) and their components such as call signs, signal reports, location and other aspects. Here’s the general structure of these conversations as background:

http://naqcc.info/cw_qsos.html

For example, from this CW string decoded from the radio:

N3AQC DE K3WWP GM TNX CALL UR 599 599 IN KITTANNING PA KITTANNING PA NAME IS JOHN JOHN HW? AR N3AQC DE K3WWP K

Extract the following: Conversation Type: Call Reply Call sign: N3AQC Signal Rpt: 599 Location: KITTANNING PA Name: JOHN

I’m new to NLP tools in Python but have some experience with deep learning networks. PyText looks interesting but with no NLP experience it’d be helpful to get some guidance at the outset around which NLP tools best match the requirements.

My main question is what NLP toolsets, ideally in Python, are best suited to quickly construct a parser for these ham radio Morse code conversations to identify the conversation type (contest, regular QSO, etc) and it’s key components?

While machine learning isn’t an absolute requirement, as there are many other forms of parsers around, it’s an area I’d like to apply to this problem as a ML learning exercise.

Thanks in advance.

Rick, W5FCX

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.