2014:Audio Fingerprinting

Description

This task is audio fingerprinting, also known as query by (exact but noisy) examples. Several companies have launched services based on such technology, including Shazam, Soundhound, Intonow, Viggle, etc. Though the technology has been around for years, there is no benchmark dataset for evaluation. This task is the first step toward building an extensive corpus for evaluating methodologies in audio fingerprinting.

Data

Database

• 10,000 songs (*.mp3) in the database, in which there is exact one song corresponding to each query. (That is, there is no out-of-vocabulary query in the query set.) This dataset is hidden and not available for download.

Query set

The query set has two parts:

• 4000 10-second clips of mp3 format: This is hidden and not available for download
• 1264 10-sec clips of mp3 format: These recordings are noisy versions of George's music genre dataset. You can download the query set via this link

These recordings were obtained via different brands of smartphone, at various locations with various kinds of environmental noise.

Evaluation Procedures

The evaluation is baesd on the two parts of the query set, with top-1 hit rate being the performance index.

Submission Format

Participants are required to submit a breakdown version of the algorithm, which includes the following two parts:

1. Database Builder

Command format:

builder %file.db.list% %dir_db%

where %file.db.list% is the input list of database audio files named as uniq_key.wav For example:

./AFP/database/00001.wav
./AFP/database/00002.wav
./AFP/database/00003.wav
./AFP/database/00004.wav
...

Output file(s) should be placed into %dir_db%

2. Matcher

Command format:

matcher %dir_db% %file.query.list% %resultFile%

where %dir_db% is the directory for the built database.

%file.query.list% is the input list of query clips, for example:

./AFP/query/q0001.wav
./AFP/query/q0002.wav
./AFP/query/q0003.wav
./AFP/query/q0004.wav
...

The result file gives retrieved result for each query. The format should be:

%main_query_file_name% %main_top_1_candiate_file_name%

For example:

q0001 00204
q0002 08964
q0003 05566
...

Time and hardware limits

Due to the potentially high number of participants in this and other audio tasks, hard limits on the runtime of submissions are specified. The time/storage limits of different steps are shown in the following table:

Steps	Time limit	Storage (hard disk) limit
builder	24 hours	3 GB
matcher	10 hours	N/A

Submissions that exceed these limitations may not receive a result.

Discussion

name / email