Program

All lectures will start at 10.15 and end at 12.00, except the one on 15 November that will instead start at 16.15.

    
04 Oct. 2021: Richard BOWDEN, University of Surrey, Guildford, UK (online)

               Sign Language Recognition, Translation and Production

Abstract

 

18 Oct. 2021: Laurent BESACIER, Université Grenoble Alpes & Naver Labs Europe, FR (online)

               Self-Supervised Learning for Low Resource Speech Task

Abstract


01 Nov. 2021: Biao ZHANG, Edinburgh University, Edinburgh, UK (on-site)

               Making End-to-End Speech Translation Sparse, Context-aware, and Multilingual

Abstract

              
15 Nov. 2021: Kyle GORMAN, Graduate Center, City University of New York & Google, Inc., USA (online) - lecture starts at 16.15.

               On "massively multilingual" natural language processing

                      Abstract
               

29 Nov. 2021:Thilo STADELMANN, Zürich Hochschule für Angewandte Wissenschaften, Zürich, CH (on-site)

              Deep-learning-based Speaker Recognition and the problem of modeling time-based features

Abstract 

       

13 Dec. 2021: Jens HJORTKAER, Danish Research Centre for Magnetic Resonance, Kgs. LyngbyDK

               Neural tracking of speech in hearing impaired listeners

Abstract 

              
13 Dec. 2021: Tanja SCHULTZ, Bremen University (on-site) (tbc)

               Silent Speech Communication