Skip to main content ↑ ↓

Notice

Please note that most of the software linked on this forum is likely to be safe to use. If you are unsure, feel free to ask in the relevant topics, or send a private message to an administrator or moderator. To help curb the problems of false positives, or in the event that you do find actual malware, you can contribute through the article linked here.
Topic: Find (rough) audio duplicates (using fingerprinting) (Read 1188 times) previous topic - next topic
0 Members and 1 Guest are viewing this topic.

Find (rough) audio duplicates (using fingerprinting)

I have a compilation with untitled tracks, and I want to identify them. This music isn't on Shazam I've tried it on all these but no luck.

I do know a Youtube channel which contains at least two of the tracks, and I suspect more. The channel has over 8,000 videos of different music uploaded.

I've used youtube-dl in Ubuntu to download all of the videos from that channel. I chose the lowest quality available from Youtube to save space, the files are in Opus ~50kbps bitrate in webm container. Should still be OK for finding matches.

I want to run a program (preferably in Linux), that will search through all these files (music from the youtube channel, and from the ~20 track compilation) and look for any duplicates/matches.  I suppose this would have to be done using some kind of audio fingerprinting, as the audio won't match exactly due to different sources/encode settings.

I see this http://www.similarityapp.com/ for Windows, maybe something like this will do the job. Any other suggestions (any maybe one for Linux?)