Panako – Acoustic Fingerprinting

Welcome to the Panako REST API.

REST API Documentation

Currently the REST API only supports one function: retrieving matches for a set of fingerprints. This is done by sending an HTTP POST request to http://localhost:8080/v1.0/match.The body of the request needs to contain the following information:

{
"fingerprints": 
		[
			{"f1":206,"f2":208,"t1":7,"t2":63},
			{"f1":140,"f2":125,"t1":12,"t2":83}
		],
"query_offset": 7,
"query_duration": 27,
}

In reality the number of fingerprints is much larger. The API should either respond with a list of matches, an empty match if nothing is found, or with an error.The response looks like this:

[
	{
		"match_start":129.7760009765625,
		"match_description":"01. One More Time.mp3",
		"match_score":226,
		"query":"",
		"match_identifier":"2041226072",
		"query_start":140,
		"query_stop":165
	}
]

Further Reading

Some relevant reading material about acoustic fingerprinting.

Credits

The Panako software was developed at IPEM, Ghent University by Joren Six.

Some parts of Panako were inspired by the Robust Landmark-Based Audio Fingerprinting Matlab implementation by Dan Ellis.

If you use Panako for research purposes, please cite the following work:

@inproceedings{six2014panako,
  author      = {Joren Six and Marc Leman},
  title       = {{Panako - A Scalable Acoustic Fingerprinting System Handling Time-Scale and Pitch Modification}},
  booktitle   = {{Proceedings of the 15th ISMIR Conference (ISMIR 2014)}}, 
  year        =  2014
}