FAQ

In the following list, we collect frequently asked questions (FAQ) with respective questions (Q) and answers (A).

  • Q: How do I have to write my paper in order to have higher chances to be accepted?
    A: Please keep in mind: Your submission will undergo the normal review process. This means that the special session chairs and/or the area chairs select reviewers, assess the reviews, and eventually decide in favour of accept or reject. We have been notified that: “special session organizers will be involved in the final decisions.” “Involved” means that we *might* be asked but that we definitely will not be able to decide. According to our experiences from the last years, all this means: Please write your paper as you would write a non-challenge paper! Performance is important for the challenge itself but not for acceptance. A badly written paper with the best results will be rejected, a well written paper with results well below the best one will have high chances to be accepted! In both cases, do not blame us organisers :-). Remember: Interspeech aims at an acceptance rate of ~ 50%. When we assume scores from 1-6, with 6: definitely accept, 5: accept, 4: weak accept, …, an average score below ~ 4,5 for a paper can be at the threshold between accept/reject. So – in order to be rejected – your paper has not to be really bad but just not convincing enough to get enough reviews with scores 5 and/or 6! Thus, write a *convincing* paper. Simply put as much effort in designing and writing the paper as you put into boosting your performance. Don’t do your experiments until the day before the deadline — reserve enough time for writing! This means everything you can read about writing scientific papers: Especially, write the introduction not only for us organisers but for an audience that is not well acquainted with the task. You do not have to describe motivation, collection and data as fully as we do in our overview paper but you have to give enough details! In the same vein, detail the procedure you chose and the results you achieve in such a way that it can be understood by the non-expert. Write clearly and check thoroughly style and English grammar – ask someone else to do close reading, if necessary. References should be complete and correct – not just one column of page 5.
  • Q: Can I upload my paper onto arXiv?
    You can upload both accepted and rejected submissions, but only *after the camera-ready deadline*, onto arXiv. Please not that especially for Covid-19 papers, arXiv might require confidence intervals for performance measures.
  • Q: Are there scripts to extract the ComParE feature set with openSMILE available?
    A: Please see here.
  • Q: Do I have to include test set results for the paper submission?
    A: Yes, if you want to participate in the competition (at least one result submission has to be made before the paper deadline); you can also submit general papers on the topic or data of the respective year. Note that you can update your reported results in the final camera ready version.
  • Q: Can we submit one paper to Interspeech describing participation in several Sub-Challenges?
    A: This is possible – obviously the paper should read well and contain all necessary details, as it needs to pass peer-review as condition for successful Challenge participation.
  • Q: Can we submit more than one paper to Interspeech describing participation in different Sub-Challenges?
    A: This is possible – you can submit, e.g., separate papers for the participation in different Sub-Challenges or for different approaches in the same Sub-Challenge. Each one will undergo peer-review independently.
  • Q: Can we have richer meta-data for the databases, so that we can also look at other things?
    A: Items not available in the download packages might be available after the Challenge at the data owners’ discretion.
  • Q: My results are below the baseline – does it make sense to submit?
    A: Of course it does. We do not know whether the baseline will be surpassed and different experiences with the tasks on the same dataset will be of interest. Please remember that all submissions to the Challenge go through the normal reviewing process. Although it is very likely that the reviewers do know – and take into account – the baselines, the criteria are the usual, i.e., scientific quality; surpassing any baseline – be this the one given for this challenge, or another one known from the literature – is just one of the criteria. A paper reporting results above the baseline, but poorly written, runs high risks *not* to be accepted; in contrast, a paper which is well written, contributing to our knowledge, but with results below the baseline, has high chances to be accepted.
  • Q: When is the deadline for submitting the results?
    A: You will need to submit results shortly prior to camera ready paper submission to INTERSPEECH as a result on test needs to be included in your final paper version if you want to compete for the Sub-Challenge awards. All except one (which has to be used before the first paper deadline) of the five result submissions per Sub-Challenge and participant can be saved for submission as late as specified in the current challenge shortly ahead of camera-ready submission.
  • Q: How will the data be distributed to the participants? Are you sending the test data at the same time with training and development partitions?
    A: Yes, we do. However, labels are only given for training and development partitions. Further, we are not sending the data – you will need to download the data. Please first download, print, and sign the license agreements – one per data set once the agreements are available – and scan and mail or fax these to the addresses given on the agreements. You will then receive an email with download instructions.
  • Q: Can I use additional databases within the Challenge?
    A: You can – as long as these are well known and accessible to everybody and you clearly state the details in your paper.
  • Q: May I participate in several Sub-Challenges?
    A: Yes, of course. Every site may participate in every Sub-Challenge and the five upload trials are per Sub-Challenge. In how many Sub-Challenges one site participates is decided at the moment you submit your paper by the results you include. Please send an additional e-mail to the organisers to indicate which Sub-Challenges you participate in for us to know.
  • Q: Do I have to submit a paper in order to participate?
    A: Yes, the submission and acceptance of a paper is mandatory. Please make sure to select the special event during the submission procedure as first option. The prizes will be awarded during INTERSPEECH.
  • Q: May I include results on other corpora in my paper?
    A: Yes, of course. As long as it fits the general focus these are of course very welcome.
  • Q: What are the other formalities with respect to the paper of mine?
    A: Please make sure to reference the official paper on the challenge and avoid repetition of the general data and Challenge description.