Interspeech 2020

This year’s Interspeech was not only the first Interspeech to be held as a virtual event but also my first Interspeech. The organizers in Shanghai did a great job at translating such a huge conference to the virtual space while catering for different time zones.

Personally, I profited the most from the longer events, such as the tutorials by Tatsuya Kawahara & Roger K. Moore, all the keynotes, and of course the events organized by the ISCA-SAC. I got to participate in a mentoring event on time management for PhD students with very helpful advice by Carol Espy-Wilson and Sarah Levitan and the students meet experts event, in which Jon Barker, Tara Sainath, Björn Schuller, and Sunayana Sitaram gave some interesting insights into their work in academia and the industry.

Finally, my fellow PhD students at UdS Iona Gessinger and Eran Raveh received the ISCA Award for Best Student Paper at Interspeech 2020 for their paper on ‘Phonetic Accommodation of L2 German Speakers to the Virtual Language Learning Tutor Mirabella’.

Workshops in early October 2020

If I had to come up with a positive aspect of the COVID-19 pandemic, it’d have to be the accessibility of a number of workshops/courses/conferences that you normally wouldn’t necessarily travel to or that wouldn’t be open to the public. Therefore, making the best out of the current situation, within the past week, I got to attend a couple of workshops and courses from home:

The first one called The Anechoic Chamber: Construction and Reception of Silence in Language, Literature, and History at Uni Bielefeld approached the concept of silence from many different disciplines including literature, culture, and musicological aspects.

The second workshop was Laughter and Other Non-Verbal Vocalisations Workshop held at Uni Bielefeld as well. Here, the focus was much more on language and phonetic aspects of laughter and all sorts of non-verbal vocalizations. It came with a poster session (which as always was too short) and two great keynotes by Khiet Truong and Greg Bryant. My group from the PINTS project also presented two posters: the one I was involved in with Jürgen Trouvain you can find on the Publications section or on the conference website and the other one from Beeke Muhlack on the project website or again the conference website.

The third one that has been going on all week is a course on Voice technology given by Finnian Kelly of Oxford Wave Research organized by UZH Zurich. The course tackles the subject of speaker recognition from a technical point of view, shedding light on both the process of automatic speaker recognition and aspects of forensic speaker recognition. I am quite sure that everyone is enjoying the course as much as I am, as Finnian does an amazing job at explaining technical and complex matters in a comprehensible way.

Launch

This page is now online and I’m looking forward to sharing all sorts of updates with you!