Forums » General Discussion Search

Problem identifying Videos backgrounds songs New Reply

Author Post
Posts: 3
Registered: Jul 12, 2012

Hello, I 've extracted a sound from a video TV Show (i.e The simpsoms). This sound contains the main voices and a background music. When I send a part of this sound (ie. 40 secs) in mp3 format trough echonest API, the system never recognize the background music. I want to recognize some background music from several videos through echonest, How Should I send the sound in order to get a good analysis? I've tried with several videos but I didn't have luck.

Thanks in Advance.

Posts: 138
Registered: Feb 07, 2012

Hi devops,

I assume that you are using the song/identify part of the API, yes? It's not really designed to be used in the situation you have described, but read on anyway.

If you are using ENMFP, then you will need to supply it with a clean excerpt, i.e., it is highly unlikely that it will work if there is speech on top of the music.

If you are using Echoprint, then there is a better chance of the music identification working properly in the presence of a small amount extra noise, but if there is a significant amount of talking over the music then it is also unlikely to work. The best thing would be to run the query using a segment of audio which has minimal talking over it (i.e., one which is mostly clean), and to run experiments to evaluate if it works in your situation.



Posts: 3
Registered: Jul 12, 2012

Hi Anesbit, Thank you very much for your reply. Well, Do you know how can I clean a sound automatically in order to work with Echoprint?. I am trying to develop an applicatio like shazam.


Reply to this Thread

You must log in to post a reply.