ELAN survey

Hey folks, there is a survey out on the future of ELAN that many of you would be eminently qualified to take part in:


Here’s the announcement tweet:

Some interesting developments described at the survey:

Together with the Cognitive Machine Learning team in Paris, we are embarking on a new project to create a cloud-based platform for the storage, annotation, and semi-automatic analysis of everyday language data. The platform will

  • enable researchers to acquire, store, annotate, analyze and share their audio-video recordings while maintaining data confidentiality
  • help researchers plan and organise annotation campaigns and
  • allow researchers to use machine learning/AI algorithms for pre-annotation tasks (e.g. pre-segment the annotation file into speech/non-speech events) and for analysis.

We are asking about your own use of ELAN to help us decide what kind of functionality to build into the new platform.

I can’t help but notice that the survey doesn’t mention language documentation or multilingual content at all.

Yeah, it sounds like just one more of these NLP/machine learning projects that in the end only work for ‘big’ languages… If they plan to gear it to documentation, this is not visible at all from the project description

1 Like

Hi @Sandra!

This is a good point. Personally, I don’t think of ELAN was ever meant to be “our” tool in the documentation community — we use it because it meets certain needs, but not all of them. There is pretty good evidence that it was never designed with language documentation in mind, and there’s even less evidence (this survey included) that we should expect much change in that direction.

I’m also wondering what the emphasis on cloud computing is all about. I guess people need that for collaboration, but of all the needs we have, that doesn’t strike me as the top of the list.

(BTW, I hope you are having fun in Oaxaca!)

it’s worth telling them this - it’s a good point!