2007:Multiple Fundamental Frequency Estimation & Tracking

Description

A complex music signal can be represented by the F0`s contours of its constituent sources which is very useful in most music information retrieval systems. There have been many attempts in multi-F0 estimation, and related area melody extraction. The goal of multiple F0 tracking is to extract contours of each source from a complex music signal. In this task we would like to evaluate the state-of-art multi-F0 tracking algorithms. Since F0 tracking of all sources in a complex audio mixture can be very hard, we have to restrict our problem space. The possible cases are:

1. Multiple instruments active at the same time but each playing monophonically (one note at a time) and each instrument having a different timbre in a single channel input.

2. Multiple sources each playing polyphonically (e.g. chords…) in a single channel input.

3. Multiple sources each playing polyphonically in a stereo panned mixture.

We are more interested in the more general but feasible first case. The third case, which is subset of first case should be considered as a subtask since in most professional recordings, sources are recorded individually and panned across two stereo channels, researchers should take advantage of that.

Data

Since extracting F0 contours of all sources is a challenging task, the number of sources should be limited to 4-5 pitched instruments (no percussions). Annotating the ground truth data is an important issue, one option is to start with midi files and use a realistic synthesizer to create the data, to have completely accurate ground truth. A real world data set can be the RWC database but this database is already available to participants. Please make your recommendations on creating a database for this task.

Evaluation

The evaluation will be similar to the previous Audio Melody Extraction Tasks, based on the voicing and F0 detection for each source. Each F0-contour extracted from the song by the proposed system will be scored by one of the ground truth contours for that song that results in the highest score. Another score based on the raw frequency estimates per frame without tracking is also going to be reported.

Comments

chunghsin yeh

Reading the above suggestion we don't understand exactly how the contours are defined. If a contour is like a melody the problem seems ill-posed. Therefore, we suppose the different contours are related to f0 note contours. The task would then consist of multiple levels of evaluation using different data sets.

1. single frame evaluation

 using either artificially mixed monophonic samples:
 -- mixing with equal/non-equal energy
 -- random mix or musical mix
 or midi recordings as suggested above

Note, however, that even with midi recordings, the ground truth is not perfect, because note end events will not necessarily align with the end of the instruments sound, unless you are not planning to interrupt the sound. One may define a tolerance range after the note off event, where the f0 of the note may or may not be detected by the algorithms. The tolerance areas are not going to be evaluated as long as the f0 detected in this area is the correct f0 of the previous note.

2. multiple frames (tracking) evaluation

  using the midi database as above.

We're willing to share our single frame database (artificial mixtures) as well as some scripts for building the reference data.

cyeh(at)ircam.fr

mert bay

Thanks for you comments Chunghsin. Contour is all the F0`s generated by a single instrument. We should make this case feasible by constraining each instrument to play continously, one note at a time and each one having a distinct timbre. So the participants will not only have to extract all the F0`s per frame, also associate the extracted F0`s with the correct timbre.

Since more people are working only on estimation, we can clearly separate the evaluations (with tracking or single frame estimation) to two different tasks so that people can only perform the F0 estimation per frame basis if they don`t want to attempt tracking. No tracking score will be reported for them.

To annotate the ground truth from midis, we can synthesize each instrument separately, use a monophonic pitch detector to estimate the F0`s. Then manually verify it.

It is great that you are willing to share data. Do you have monophonic recordings of instruments playing solo passages or just single notes? If you have solo passages, we can also use it for tracking evaluation dataset. We can mix them artificially. The mix might not be musically meaningful however it will be good to obtain accurate ground truth.

chunghsin yeh

F0 contour detection as you have defined can only be done for case 1: "Multiple instruments active at the same time but each playing monophonically ..."

To our understanding, there are two levels of F0 tracking:

1. tracking note contours without taking into account the instrument timbre (possible for case 1-3)

2. tracking note contours with similar instrument timbre (for case 1 only)

Therefore, our suggestion would be to have three levels of evaluation: single frame, note contour and instrument contour.

We have artificial mixtures of single notes using databases of McGill, Iowa, IRCAM amd RWC. We also have a collection solo instrument recordings but we would like to study the rights issues.

cyeh(at)ircam.fr

mert bay

Yes, the instrument tracking can only be done feasibly for case 1. We can have these 3 levels of evaluation as you said, with different datasets and participants can submit their systems to whichever is suitable. I guess we won`t have problem about creating a dataset from artificial mixtures of single notes. We are planning to organize a recording session, to record each instrument separately in a quintet but at the end we`ll only have a limited amount of data. We appreciate if you can share your collection of instrument recordings. That data will not be public, only be used for evaluation purposes.

Eric Nichols

I am interested in participating, although I hope that this task ends up using real audio recordings for the competition this year. I am not particularly interested in the results of using artificially synthesized audio -- even though it may ease the creation of ground truth, it seems to invite different sorts of solutions than one would develop for the general case of polyphonic audio recognition.

I suggest that this task uses real recordings that have been annotated. This annotation can be accomplished by performing an automated match between a score/MIDI file and audio recording, and then the automated match can be hand-tuned to ensure reliable ground truth. I agree that the task should deal with monophonic audio.

I don't see why the distinction should be made between monophonic and polyphonic instruments -- a system to track multiple f0s should handle two flutes in the same mammer as a funny "polyphonic flute", just as it should handle a monophonic line on a piano as well as chords on a piano. I suppose this is because I am biased by an interest in reducing audio to "piano reduction"-type scores, and I'm not as interested in detecting the particular instruments playing each note.

I would furthur suggest starting with rather simple instrumental pieces, to facilitate creation of the annotation and to simplify the problem domain, which is very complex. For example, small chamber pieces such as duos, trios, quartets, etc., simple piano pieces and perhaps even simple examples of full orchestral music could be included.

Mert Bay

I would like to announce that we are going to be using real audio. Recently we did the first stage of the recording session here in Univ. of Illinois, where a professional quinted (flute, bassoon, clarinet,horn, oboe) played a 6 minute piece by Beethoven, recorded close mic`ed. The next stage would be to get every performer one by one to record indiviudual tracks while the performer is listening to the rest of the instruments through headphones. We can get the ground truth using a monophonic pitch detector and then hand correct the contours. Combinations of 2-3-4 out 5 tracks of 30 second incipits can be used as our dataset. I`ll upload a portion of the data as a development set once the the recordings are completed.

The polyphonic instruments will cause problems in most trackers, although there are no problems for F0 estimation (then evaluate on frame by frame basis). Do you suggest that the systems should output the F0`s of the polyphonic instrument in on track? We can create another category for that if more than 3 people wants their system to be evaluated in that category.

The reason for evaluation on the note contour basis is, some systems which tracks according to the continuity of the spectrum tends to lock into a note of a particular instrument without taking into account the timbre but when the note ends and its energy gets weaker, the system will start to track another note of another intrument. If your system can perform tracking on the instrument level fine, then it shouldn`t be problem for you to segment the note boundaries. Ofcourse you don`t have to be evaluated in that if you don`t want to.

As a discussed above, for right now three levels of evaluation is being considered

1. Evaluate the F0 esimators: Frame by frame basis. Systems should output the active frequencies in each frame. This dataset can have polyphonic instruments.

2. Evaluate F0 trackers on note level. Each system should output a F0 contour for each note from each instrument. This data can also have polyphonic instruments

3. Evaluate F0 trackers on instrument level. Each system should output the F0 contour of each instrument.

Eric Nichols

Thanks for the clarification. I still have a few more questions. I'm mostly interested in version 1 of the task above, if I understand things correctly. Our algorithm outputs a set of sounding notes at each frame, without tracking individual instruments. Please correct me if this is wrong, but I think that this means that task 1 is the correct one for this system.

I also would like to know what is meant by frequency tracking -- our system outputs symbolic sets of sounding notes (i.e. MIDI numbers), not actual frequency in Hz. Is this task concerned with tracking the fine-tuning of each note over time?

Finally, in the proposed task, are the instruments known ahead of time, for use in training/tuning algorithms for those particular sounds? For instance, should the participating systems be tuned for flute, bassoon, clarinet, horn, and oboe?

Mert Bay

Since your algorithm peforms only F0 estimation not tracking, first evaluation criteria is suitable for you. For the first criteria, the estimated F0s will be evaluated as correct if it is in a semitone range (+ or - quarter tone) of the ground truth F0s for that frame. Every reported F0 will be checked against the closest F0 in the ground truth. The algorithms will report a set of F0s every 10 ms. I suggest, the systems should know the total number of sources in the piece before hand. However each source will not be active in every frame. For the second criteria, we have to decide on a reasonable range for onset / offset timings for the reported notes as opposed the ground truth timings. Third criteria will be evaluated like the first one except this time each reported F0-track for the whole piece will be evaluated against the closest ground truth F0 track. If the instrument is not active, the system should report an F0 of 0Hz, or midi note number 0.

For the 3rd evaluation criteria, the systems will have the oppurtunity to be tuned for the instruments which is not necessary for F0 estimation. That`s why we will soon release a small training set of individual tracks of a woodwind quintet playing a highly counterpuntal piece.

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

Moderators

Mert Bay mertbay@uiuc.edu,Andreas Ehmann aehmann@uiuc.edu,Anssi Klaupri klap@cs.tut.fi