2008:Multiple Fundamental Frequency Estimation & Tracking

Description

That a complex music signal can be represented by the F0 contours of its constituent sources is a very useful concept for most music information retrieval systems. There have been many attempts at multiple (aka polyphonic) F0 estimation and melody extraction, a related area. The goal of multiple F0 estimation and tracking is to identify the active F0s in each time frame and to track notes and timbres continuously in a complex music signal. In this task, we would like to evaluate state-of-the-art multiple-F0 estimation and tracking algorithms. Since F0 tracking of all sources in a complex audio mixture can be very hard, we are restricting the problem to 3 cases:

1. Estimate active fundamental frequencies on a frame-by-frame basis.

2. Track note contours on a continuous time basis. (as in audio-to-midi). This task will also include a piano transcription sub task.

3. Track timbre on a continous time basis.

Data

A woodwind quintet transcription of the fifth variation from L. van Beethoven's Variations for String Quartet Op.18 No. 5. Each part (flute, oboe, clarinet, horn, or bassoon) was recorded separately while the performer listened to the other parts (recorded previously) through headphones. Later the parts were mixed to a monaural 44.1kHz/16bits file.

Synthesized pieces using RWC MIDI and RWC samples. Includes pieces from Classical and Jazz collections. Polyphony changes from 1 to 4 sources.

Polyphonic piano recordings generated using a disklavier playback piano.

So, there are 6, 30-sec clips for each polyphony (2-3-4-5) for a total of 30 examples, plus there are 10 30-sec polyphonic piano clips. Please email me about your estimated running time (in terms of n times realtime), if we believe everybodyΓÇÖs algorithm is fast enough, we can increase the number of test samples. (There were 90 x real-time algo`s for melody extraction tasks in the past.)

All files are in 44.1kHz / 16 bit wave format. The development set can be found at Development Set for MIREX 2007 MultiF0 Estimation Tracking Task.

Send an email to mertbay@uiuc.edu for the username and password.

Evaluation

This year, We would like to discuss different evaluation methods. From last year`s result, it can be seen that on note tracking, algorithms performed poorly when evaluated using note offsets. Below is the evaluation methods we used last year:

For Task 1 (frame level evaluation), systems will report the number of active pitches every 10ms. Precision (the portion of correct retrieved pitches for all pitches retrieved for each frame) and Recall (the ratio of correct pitches to all ground truth pitches for each frame) will be reported. A Returned Pitch is assumed to be correct if it is within a half semitone (+ - 3%) of a ground-truth pitch for that frame. Only one ground-truth pitch can be associated with each Returned Pitch. Also as suggested, an error score as described in Poliner and Ellis p.g. 5 will be calculated. The frame level ground truth will be calculated by YIN and hand corrected.

For Task 2 (note tracking), again Precision (the ratio of correctly transcribed ground truth notes to the number of ground truth notes for that input clip) and Recall (ratio of correctly transcribed ground truth notes to the number of transcribed notes) will be reported. A ground truth note is assumed to be correctly transcribed if the system returns a note that is within a half semitone (+ - 3%) of that note AND the returned note`s onset is within a 50ms range( + - 25ms) of the onset of the ground truth note, and its offset is within 20% range of the ground truth note`s offset. Again, one ground truth note can only be associated with one transcribed note.

The ground truth for this task will be annotated by hand. An amplitude threshold relative to the file/instrument will be determined. Note onset is going to be set to the time where its amplitude rises higher than the threshold and the offset is going to be set to the the time where the note`s amplitude decays lower than the threshold. The ground truth is going to be set as the average F0 between the onset and the offset of the note. In the case of legato, the onset/offset is going to be set to the time where the F0 deviates more than 3% of the average F0 through out the the note up to that point. There is not going to be any vibrato larger than a half semitone in the test data.

Different statistics can also be reported if agreed by the participants.

Antonio's comments 24/07/08

First of all, thanks to the Mirex team for their effort to make it possible again. Just some comments about the evaluation this year.

As the first multiple f0 contest took place last year, it was very welcomed and many researchers submitted their algorithms, so the results in Mirex07 provided a very valuable resource for comparing different approaches. However, the participation will probably not be so massive this year so, in case that the database used for evaluation will not be the same than last year, it would be nice to report (if possible) both the results obtained using the Mirex07 database and the results with the Mirex08 database, to directly compare the new approaches with the algorithms presented last year.

Emmanuel's comments 25/07/08

As last year, we will participate in tasks 1 and 2 only.

For task 2, I understand that the proposed annotation method will take reverberation into account, so that for instance the offset of one note will happen after the onset of the following note in a legato context. Is that true? Computing the amplitudes of the notes is not trivial in the presence of overlapping partials, so I wonder if Mert could tell us a bit more.

Results could also be evaluated with the onset-only metric used last year.

Mert`s comments

Thanks for the comments. Antonio, the new dataset will be the previous year`s plus some more. So last year`s labs can compare their new methods. Emmanuel, the current ground truth is annotated in a non overlapping way. So within the source, the offset of the previous note can not happen after the onset of the current one. The offset range in the evaluation criteria should be enough to not the cause a false negative because of the reverberation. However, we can come up with a better criteria for evaluating the with the offsets.

Antonio's comments 30/07/08

We will participate in tasks 1 and 2 too. Mert, any new about the deadline to send the algorithms?

Jean-Louis's comments 30/07/08

We will probably participate to task 1. One question about the development set: I know the groundtruth is annotated at frame level, with a hop size of 10ms between the windows. However, could we know the size of the windows and the weighting window that were used? I would also like to know whether the first window starts at 0s or is centered around 0s. the ISMIR 2004 database had time stamps giving the center of each window. I wanted to check whether the annotation protocole was the same or not.

Potential Participants

If you might consider participating, please add your name and email address here and also please sign up for the Multi-F0 mail list: Multi-F0 Estimation Tracking email list

1. Vishweshwara Rao (Indian Institute of Technology Bombay) (vishu_rao@iitb.ac.in)
2. Gustavo Reis (Polytecnic Institute of Leiria, Portugal) (gustavo.reis@estg.ipleiria.pt)
3. Antonio Pertusa and José M. Iñesta (University of Alicante, Spain) (pertusa@ua.es, inesta@dlsi.ua.es)
4. Pablo Cancela (pcancela@gmail.com)
5. Emmanuel Vincent (emmanuel.vincent (at) irisa_fr) and Nancy Bertin (nancy.bertin (at) enst_fr) 6. Jean-Louis Durrieu (durrieu AT enst DOT fr) (task 1, maybe...)