Article accepted to IEEE/ACM Transactions on Audio, Speech and Language Processing.

On 28/9/2017, we got an article accepted to the special issue of IEEE/ACM Transactions on Audio, Speech and Language Processing. The article is a result of our collaboration with Daryush D. Mehta and Jarrad Van Stan from the Eye and Ear, Massachusetts General Hospital. The title of the article is “Modal and non-modal voice quality classification using acoustic and electroglottographic features”. It analyses a set of glottal source, vocal tract and harmonic model features in the task of voice quality classification. In a nutshell, we are trying to predict whether the speaker will speak in a breathy, normal, strained or rough voice. The figure below summarizes the achieved results.

res_COVAREP

The initial manuscript was sent for peer-review in December 2016. The special issue is expected to come out by the end of this year and the links to the paper will be available in a few weeks, hopefully :). For this paper, we used recordings of normal people mimicking the asked voice quality so our next target is to extend the results to a much bigger database, which contains recordings of patients with various voice disorders. So stayed tuned, if things go well, we might make our way to Seoul in 2018 for the ICASSP conference with new results.

Happy pictures of all authors below (Michal, Daryush, Jarrad, Jón).

 

Interspeech 2017 Conference Summary

Yu-Ren gave a really good talk about measuring voice severity.

Image uploaded from iOS2

Then, on Wednesday Anna, Inga, Matthías, and Jón answered questions about their posters to conference attendees.

Image uploaded from iOS15

During the conference, welcome reception, and the banquet we reconnected with many old colleagues and met many new  in the speech processing and speech recognition world. For anyone who didn’t get a chance to attend Yu-Ren’s talk or to see the posters by Jón and Inga, we have links at the bottom of the post.

This slideshow requires JavaScript.

Anna’s data is also available on Malfong now.

Inga’s Icelandic Parliament ASR Corpus

Yu-Ren’s slides

Jón’s Eyra Speech Corpora Poster

We hope to see you next year!

LVL goes to Hungary

Eydisphoto

In September Eydís will be representing our group at the CogInfoCom 2017 Conference. This will be LVL’s second time at CogInfoCom in Hungary, and we hope it will be an exciting conference with valuable insights. She will be presenting her paper “Cognitive workload classification using cardiovascular measures and dynamic features.” This will be Eydís’ last conference and paper before her study abroad semester starts later this year. So we hope she stays healthy and enjoys her time in Hungary.

 

AI Festival

The annual AI Festival was held at Reykjavik University two weeks ago on Nov 11, 2016. The focus of this year’s festival was AI and the economy. You can watch the entirety of the talks and discussions here (it was streamed live). There was no admission fee and the festival was open to everyone.

Many interesting lectures and discussions, including the one by Dr. Jacky Mallett, where they had written software to simulate an economy with several interesting results, but I have to mention here as she did at the beginning of the talk that

All economies described in this talk are artificial. Any relationship to any real economy is an open research problem.

and in fact that

This warning should be attached to all academic presentations on economics.

After the talks and discussions, there was a poster & demonstration session titled Innovation & AI in Industry & Academia where many people from within the University came to present their projects to interested parties. There were snacks, there was beer, there was fun and knowledge and ideas were shared.

The Language and Voice Lab of course had a strong presence there with 5 posters.

  • Automatic Speech Recognition for Simulated Air Traffic Control
  • Automatic speech recognition for Icelandic (two projects, Free and open large vocabulary ASR and ASR for parliament speeches)
  • Cognitive workload monitoring using voice
  • Eyra – data acquisition system for many languages
  • Objective Assessment of Voice Quality

You can see more about our projects here on this site, and of course you can contact us if you want further information.

This slideshow requires JavaScript.

 

Here’s the program:
14.00 Introduction Dr. Kristinn R. Þórisson
– Professor at RU, Director of IIIM
14.10 Towards an Evolutionary Theory of Technological Change
Prof. J. Doyne Farmer
– Director of Complexity Economics, Institute for New Economic Thinking, University of Oxford
15.00 Coffee
15.15 AI & Economics: Problem or Opportunity?
Dr. Jacky Mallett
– IIIM Senior Scientist / Adjunct Professor, Reykjavik University
15:50 Position statements: AI & the Economy: Monkeywrench or Moneysaver?
– Dr. Jón Gudnason, Dr. Magnús Torfason, Dr. Kristinn R. Thórisson
16.05 Coffee
16.15 Panel Discussion: AI & the Economy: Monkeywrench or Moneysaver?
Moderator: Jacky Mallett
17.15 Innovation & AI in Industry & Academia (room M201)
– Posters & Demonstrations / Refreshments