Tagged: automatic signal identification

SignalID: Shazam Style Automatic Signal Identification for Android

SignalID is a new Android app available on the Google Play store which offers Shazam-like radio signal identification. Just like Shazam does for music, you simply tune to an unknown signal with your SDR, play the raw audio, and let the app listen to it for five seconds. It then computes an audio fingerprint and checks to see if it knows what the signal is. 

We tested the app but unfortunately we were unable to get it to detect any signals. Please write in the comments if you have success. As it uses audio fingerprinting, the app is probably highly dependant on choosing the correct demodulator (AM/FM/SSB etc), and also the tuning and signal quality. We note that most of the signal sources seem to come from our sister site the Signal ID Wiki. Searching through the wiki is a good alternative if automated solutions fail.

However the the app is new and we expect improvements and more signals to be added in the future. Currently the following signals can be recognized: 

- RTTY (Commercial 85Hz, 170Hz, 450Hz, 850Hz, Amateur 170Hz)
- PactorI (Standard, FSP, FEC, SELCALL)
- ASCII (170Hz)
- ALIS
- Codan8580 (200Hz, 250Hz)
- CIS36_50
- CIS40_5
- CIS50_50
- STANAG 4285 (GEN, SYS3000 FEC, 8PSK, TFC, IDLE, SYS3000)
- FT4

- FT8
- WEFAX (120, 240)
- 2G ALE
- 3G ALE
- CHIP64
- APRS (Burst)
- ATIS
- Tetrapol
- POCSAG
- FLEX (2FSK)
- PSK (31, 63, 125, 250, 500)

We note that this app reminds us of a Python based signal identification app for the PC called "audio_recognition_system" which we posted about earlier this year.

SignalID: Shazam-like audio based signal identification for Android.
SignalID - Demonstration

Shazam Style Automatic Signal Identification via the Sigidwiki Database

Thank you to José Carlos Rueda for submitting news about his work on converting a "Shazam"-like Python program made originally for song identification into a program that can be used to automatically identify radio signals based on their demodulated audio sounds. Shazam is a popular app for smartphones that can pull up the name of any song playing within seconds via the microphone. It works by using audio fingerprinting algorithms and a database of stored song fingerprints.

Using similar algorithm to Shazam, programmer Joseph Balikuddembe created an open source program called "audio_recogition_system" [sic] which was designed for creating your own audio fingerprint databases out of any mp3 files.

José then had the clever idea to take the database of signal sounds from sigidwiki.com, and create an identification database of signal sounds for audio_recogition_system. He writes that from his database the program can now identify up to 350 known signals from the sigidwiki database. His page contains the installation instructions and a link to download his premade database. The software can identify via audio that is input from the PC microphone/virtual audio cable or from a file.

Fingerprinted Audio Samples of Radio Signals
Fingerprinted Audio Samples of Radio Signals