2005:Audio Onset Detect

Proposer

Paul Brossier (Queen Mary) paul.brossier@elec.qmul.ac.uk

Pierre Leveau (Laboratoire d'Acoustique Musicale, GET-ENST (Télécom Paris)) leveau at lam dot jussieu dot fr

Title

Onset Detection Contest

Description

The aim of this contest is to compare state-of-the-art onset detection algorithms on music recordings. The methods will be evaluated on a large, various and reliably-annotated dataset, composed of sub-datasets grouping files of the same type.

1) Input data

Audio format:

The data are monophonic sound files, with the associated onset times and data about the annotation robustness.

• CD-quality (PCM, 16-bit, 44100 Hz)
• single channel (mono)
• file length between 2 and 36 seconds (total time: 14 minutes)
• File names:

Audio content:

The dataset is subdivided into classes, because onset detection is sometimes performed in applications dedicated to a single type of signal (ex: segmentation of a single track in a mix, drum transcription, complex mixes databases segmentation...). The performance of each algorithm will be assessed on the whole dataset but also on each class separately.

The dataset contains 85 files from 5 classes annotated as follows:

• 30 solo drum excerpts cross-annotated by 3 people
• 30 solo monophonic pitched instruments excerpts cross-annotated by 3 people
• 10 solo polyphonic pitched instruments excerpts cross-annotated by 3 people
• 15 complex mixes cross-annotated by 5 people

Moreover the monophonic pitched instruments class is divided into 6 sub-classes: brass (2 excerpts), winds (4), sustained strings (6), plucked strings (9), bars and bells (4), singing voice (5).

Nomenclature

<AudioFileName>.wav for the audio file

2) Output data

The onset detection algoritms will return onset times in a text file: <Results of evaluated Algo path>/<AudioFileName>.output.

Onset file Format

<onset time(in seconds)>\n

where \n denotes the end of line. The < and > characters are not included.

Participants

• Julien Ricard and Gilles Peterschmitt (no affiliation, algorithm previously developped at University Pompeu Fabra), julien.ricard@gmail.com, gpeter@iua.upf.es
• Axel Roebel (IRCAM), roebel@ircam.fr
• Antonio Pertusa, Jos├⌐ M. I├▒esta (University of Alicante) and Anssi Klapuri (Tampere University of Technology), pertusa@dlsi.ua.es, inesta@dlsi.ua.es, klap@cs.tut.fi
• Alexandre Lacoste and Douglas Eck (University of Montreal), lacostea@sympatico.ca, eckdoug@iro.umontreal.ca
• Nick Collins (University of Cambridge), nc272@cam.ac.uk
• Paul Brossier (Queen Mary, University of London), paul.brossier@elec.qmul.ac.uk
• Kris West (University of East Anglia), kw@cmp.uea.ac.uk

Other Potential Participants

• Balaji Thoshkahna (Indian Institute of Science,Bangalore), balajitn@ee.iisc.ernet.in
• MIT, MediaLab

Tristan Jehan <tristan{at}medialab{dot}mit{dot}edu>

• LAM, France

Pierre Leveau <leveau at lam dot jussieu dot fr> Laurent Daudet <daudet at lam dot jussieu dot fr>

• IRCAM, France

Xavier Rodet (rod{at}ircam{dot}fr), Geoffroy Peeters (peeters{at}ircam{dot}fr);

Evaluation Procedures

The detected onset times will be compared with the ground-truth ones. For a given groud-truth onset time, if there is a detection in a tolerance time-window around it, it is considered as a correct detection (CD). If not, there is a false negative (FN). The detections outside all the tolerance windows are counted as false positives (FP). Doubled onsets (two detections for one ground-truth onset) and merged onsets (one detection for two ground-truth onsets) will be taken into account in the evaluation. Doubled onsets are a subset of the FP onsets, and merged onsets a subset of FN onsets.

We define:

Precision

P = Ocd / (Ocd +Ofp)

Recall

R = Ocd / (Ocd + Ofn)

and the F-measure:

F = 2*P*R/(P+R)

with these notations:

Ocd: number of correctly detected onsets (CD)

Ofn: number of missed onsets (FN)

Om: number of merged onsets

Ofp: number of false positive onsets (FP)

Od: number of double onsets

Other indicative measurements:

FP rate:

FP = 100. * (Ofp) / (Ocd+Ofp)

Doubled Onset rate in FP

D = 100 * Od / Ofp

Merged Onset rate in FN

M = 100 * Om / Ofn

Because files are cross-annotated, the mean Precision and Recall rates are defined by averaging Precision and Recall rates computed for each annotation.

To establish a ranking (and indicate a winner...), we will use the F-measure, widely used in string comparaisons. This criterion is arbitrary, but gives an indication of performance. It must be remembered that onset detection is a preprocessing step, so the real cost of an error of each type (false positive or false negative) depends on the application following this task.

Evaluation measures:

• percentage of correct detections / false positives (can also be expressed as precision/recall)
• time precision (tolerance from +/- 50 ms to less). For certain file, we can't be much more accurate than 50 ms because of the weak annotation precision. This must be taken into account.
• separate scoring for different instrument types (percussive, strings, winds, etc)

More detailed data:

• percentage of doubled detections
• speed measurements of the algorithms
• scalability to large files
• robustness to noise, loudness

Relevant Test Collections

Audio data are commercial CD recordings, recordings made by MTG at UPF Barcelona and excerpts from the RWC database. Annotations were conducted by the Centre for Digital Music at QMU London (62% of annotations), Musical Acoustics Lab at Paris 6 University (25%), MTG at UPF Barcelona (11%) and Analysis Synthesis Group at IRCAM Paris (2%). MATLAB annotation software by Pierre Leveau (http://www.lam.jussieu.fr/src/Membres/Leveau/SOL/SOL.htm ) was used for this purpose. Annotaters were provided with an approximate aim (catching all onsets corresponding to music notes, including pitched onsets and not only percussive ones), but no further supervision of annotation was performed.

The defined ground-truth can be critical for the evaluation. Precise instructions on which events to annotate must be given to the annotators. Some sounds are easy to annotate: isolated notes, percussive instruments, quantized music (techno). It also means that the annotations by several annotators are very close, because the visualizations (signal plot, spectrogram) are clear enough. Other sounds are quite impossible to annotate precisely: legato bowed strings phrases, even more difficult if you add reverb. Slightly broken chords also introduce ambiguities on the number of onsets to mark. In these cases the annotations can be spread, and the annotation precision must be taken into account in the evaluation.

Article about annotation by Pierre Leveau et al.: http://www.lam.jussieu.fr/src/Membres/Leveau/ressources/Leveau_ISMIR04.pdf

Review 1

Besides being useful per se, onset detection is a pre-processing step for further music processing: rhythm analysis, beat tracking, instrument classification, and so on. It would be interesting that the proposal shortly discusses whether the evaluation metrics are unbiased wrt to the different potential applications.

In order to decide which algorithm is the winner a single number should be finally extracted. A possibility to do so is tuning the algorithms to a single working point on the ROC curve, e.g. say allow a difference between FP and FN of less than 1%. The evaluation should account for a statistical significance measure. I suppose McNemar's test could do the job.

It does not mention whether there will be training data available to participants. To my understanding, evaluation on the following three subcategories is enough: monophonic instrument, polyphonic solo instrument and complex mixes.

I cannot tell whether the suggested participants are willing to participate. Other potential candidates could be: Simon Dixon, Harvey Thornburg, Masataka Goto.

Review 2

Onset detection is a first step towards a number of very important DSP-oriented tasks that are relevant to the MIR community. However I wonder if it is too-low level to be of interest to the wider ISMIR bunch. I think the authors need to justify in clear terms the gains to the MIR community of carrying such an evaluation exercise.

The problem is well defined, however the author needs to take care when defining the task of onset detection for non-percussive events (e.g. bowed onset from a cello) or for non-musical events (e.g. breathing, key strokes that produce transient noise in the signal). Evaluations need to consider these cases.

The list of participants is good. I would add to the list Nick Collins and Stephen Hainsworth from Cambridge U., Chris Duxbury and Samer Abdallah from Queen Mary, and perhaps Chris Raphael from Indiana University.

The evaluation procedures are not clear to me. The current proposal is quite verbose, I will suggest that the author reduces the length of the proposal and makes it more assertive. There seems to be a few different possibilities for evaluation: measuring the precision/recall of the algorithms against a database of hand-labeled onsets (from different genres/instrumentations); measuring the temporal localization of detected onsets against a database of &amp;quot;precisely-labeled&amp;quot; onsets (perhaps from MIDI-generated sounds); measuring the computational complexity of the algorithms; measuring their scalability to large sound files; and measuring their robustness to signal distortion/noise. I think the first three evaluations are a must, and that the last two evaluations will depend on the organizers and the feedback from the contestants. For the first two evaluations, there needs to be a large set of ground truth data. The ground truth could be generated using the semi-automatic tool developed by Leveau et al. Each sound file needs to be cross-annotated by a set of different annotators (5?), such that the variability between the different annotations is used to define the &amp;quot;tolerance window&amp;quot; for each onset. Onsets with too-high variance in their annotation should be discarded for the evaluation (obviously also eliminating from the evaluation the false positives that they might produce). Onsets with very little variance can be used to evaluate the temporal precision of the algorithms. You should expect, for example, percussive onsets in low polyphonies to present low variance in the annotations, while non-percussive onsets in, say, pop music are more likely to present a high variance in their annotations. These observations on the annotated database, could be already of great interest to the community. Additionally, if the evaluated systems output some measure of the reliability of their detections, you should incorporate that into your evaluation procedures. I am not entirely sure how could you do that, so it is probably a matter for discussion within the community.

Regarding the test data, I cannot see why sounds should be monophonic and not polyphonic. Most music is polyphonic and for results to be of interest to the community the test data should contain real-life cases. I will also suggest keeping the use of MIDI sounds to the minimum possible. Separating results by type of onset (e.g. percussive, pop, etc) seems a logical choice, so I agree with the author on that the dataset should comprise music that covers the relevant categories. I personally prefer the classification of onsets according to the context on which they appear: onsets on pitched percussive music (e.g. piano and guitar music), onsets on pitched non-percussive music (e.g. string and brass music, voice or orchestral music), onsets on non-pitched percussive music (e.g. drums) and a combination of the above (&amp;quot;complex mixes&amp;quot;, e.g. pop, rock and jazz music, presenting leading instruments such as voice and sax, combined with drums, pianos and bass in the background). I don't think a classification regarding monophonic and polyphonic instruments is that relevant.

Downie's Comments

1. Tend to agree that this is a rather low level and not very sexy task to evaluate in the MIR context. However, I have great respect for folks working in this area and will defer to the judgement of the community on the suitablility of this task as part of our evaluation framework.

2. Like many of these proposals, the dependence on annontations appears to be one of the biggests hurdles. If we cannot get the suitable annotations done in time, is there a doable sub-set of this that we might run as we prepare for future MIREXes?

cheap hydrocodone buy hydrocodone

phentermine buy phentermine phentermine online order phentermine cheap phentermine phentermine diet pill phentermine online pharmacy buy phentermine online order phentermine online phentermine prescription purchase phentermine phentermine adipex phentermine pill phentermine diet phentermine side effects cheapest phentermine phentermine information phentermine on line buy cheap phentermine discount phentermine phentermine cod phentermine hcl cheap phentermine online

Proper Use of This Medicine 

Take this medicine with food or a full glass (8 ounces) of water to lessen stomach irritation.

Do not take this medicine if it has a strong vinegar-like odor. This odor means the aspirin in it is breaking down. If you have any questions about this, check with your health care professional.

Take this medicine only as directed by your medical doctor or dentist. Do not take more of it, do not take it more often, and do not take it for a longer time than your medical doctor or dentist ordered. This is especially important for children and elderly patients, who are usually more sensitive to the effects of these medicines. If too much of a narcotic analgesic is taken, it may become habit-forming (causing mental or physical dependence) or lead to medical problems because of an overdose. Also, taking too much aspirin may cause stomach problems or lead to medical problems because of an overdose.

If you think that this medicine is not working as well after you have been taking it for a few weeks, do not increase the dose. Instead, check with your medical doctor or dentist.

DosingΓÇö

The dose of these medicines will be different for different patients. Follow your doctor's orders or the directions on the label. The following information includes only the average doses of these medicines. If your dose is different, do not change it unless your doctor tells you to do so.

The number of capsules or tablets that you take depends on the strength of the medicine and on the amount of pain you are having.

For aspirin, caffeine, and dihydrocodeine For oral dosage form (capsules): For pain: AdultsΓÇö2 capsules every four hours as needed. ChildrenΓÇöDose must be determined by your doctor. For aspirin and codeine For oral dosage form (tablets): For pain: AdultsΓÇö1 or 2 tablets every four hours as needed. ChildrenΓÇöDose must be determined by your doctor. For aspirin, codeine, and caffeine For oral dosage form (tablets): For pain: AdultsΓÇö1 or 2 tablets every four hours as needed. ChildrenΓÇöDose must be determined by your doctor. For buffered aspirin, codeine, and caffeine For oral dosage form (tablets): For pain: AdultsΓÇö1 or 2 tablets every four hours as needed. ChildrenΓÇöDose must be determined by your doctor. For hydrocodone and aspirin For oral dosage form (tablets): For pain: AdultsΓÇö1 or 2 tablets every four to six hours as needed. ChildrenΓÇöDose must be determined by your doctor. For oxycodone and aspirin For oral dosage form (tablets): For pain: AdultsΓÇö1 or 2 half-strength tablets, or 1 full-strength tablet, every four to six hours as needed. Children up to 6 years of ageΓÇöUse is not recommended. Children 6 to 12 years of ageΓÇöOne-quarter of a half-strength tablet every six hours as needed. Children 12 years of age and olderΓÇöOne-half of a half-strength tablet every six hours as needed. For pentazocine and aspirin For oral dosage form (tablets): For pain: AdultsΓÇö2 tablets three or four times a day as needed. ChildrenΓÇöDose must be determined by your doctor. For propoxyphene and aspirin For oral dosage form (capsules): For pain: AdultsΓÇö1 capsule every four hours as needed. ChildrenΓÇöDose must be determined by your doctor. For propoxyphene, aspirin, and caffeine For oral dosage form (capsules or tablets): For pain: AdultsΓÇö1 capsule or tablet every four hours as needed. ChildrenΓÇöDose must be determined by your doctor.

hydrocodone hydrocodone online buy hydrocodone hydrocodone vicodin hydrocodone order hydrocodone addiction buy hydrocodone online hydrocodone ap ap hydrocodone side effects cheap hydrocodone hydrocodone bitartate purchase hydrocodone hydrocodone on line hydrocodone overnight buy hydrocodone where hydrocodone online pharmacy hydrocodone cod hydrocodone withdrawal hydrocodone prescription buy hydrocodone cod cod hydrocodone hydrocodone apap 5 hydrocodone cod only order hydrocodone online

If your medical doctor or dentist has ordered you to take this medicine according to a regular schedule and you miss a dose, take it as soon as you remember. However, if it is almost time for your next dose, skip the missed dose and go back to your regular dosing schedule. Do not double doses.

StorageΓÇö

To store this medicine:

Keep out of the reach of children. Overdose is very dangerous in young children. Store away from heat and direct light. Do not store this medicine in the bathroom, near the kitchen sink, or in other damp places. Heat or moisture may cause the medicine to break down. Do not keep outdated medicine or medicine no longer needed. Be sure that any discarded medicine is out of the reach of children.

Precautions While Using This Medicine If you will be taking this medicine for a long time (for example, for several months at a time), your doctor should check your progress at regular visits.

Check the labels of all nonprescription (over-the-counter [OTC]) and prescription medicines you now take. If any contain a narcotic, aspirin, or other salicylates, check with your health care professional. Taking them together with this medicine may cause an overdose.

This medicine will add to the effects of alcohol and other CNS depressants (medicines that slow down the nervous system, possibly causing drowsiness). Some examples of CNS depressants are antihistamines or medicine for hay fever, other allergies, or colds; sedatives, tranquilizers, or sleeping medicine; other prescription pain medicine or narcotics; barbiturates; medicine for seizures; muscle relaxants; or anesthetics, including some dental anesthetics. Also, stomach problems may be more likely to occur if you drink alcoholic beverages while you are taking aspirin. Do not drink alcoholic beverages, and check with your medical doctor or dentist before taking any of the medicines listed above, while you are using this medicine .

Taking acetaminophen or certain other medicines together with the aspirin in this combination medicine may increase the chance of unwanted effects. The risk will depend on how much of each medicine you take every day, and on how long you take the medicines together. If your medical doctor or dentist directs you to take these medicines together on a regular basis, follow his or her directions carefully. However, do not take acetaminophen or any of the following medicines together with this combination medicine for more than a few days, unless your medical doctor or dentist has directed you to do so and is following your progress:

vicodin buy vicodin buy vicodin online vicodin online pharmacy vicodin es vicodin online hydrocodone vicodin order vicodin online order vicodin vicodin without prescription generic vicodin vicodin side effects vicodin addiction vicodin prescription purchase vicodin vicodin withdrawal cheap vicodin vicodin detox vicodin picture vicodin cod vicodin withdrawal symptom vicodin hp vicodin tablet valium vicodin vicodin es tablet where to buy vicodin vicodin withdrawl snorting vicodin vicodin abuse vicodin overdose vicodin effects buy cheap vicodin m357 vicodin