2020 JSALT Closing Ceremonies

Below is the schedule for the 2020 JSALT Closing Ceremonies, as well as video playlists of both final presentations. 

August 6: 9 AM-12:00 PM EDT Speech Recognition and Diarization for Unsegmented Multi-talker Recordings Team Presentation


  • 9:00-9:10 EDT: Welcome Remarks (Najim Dehak, Sanjeev Khudanpur and Jan Trmal)
  • 9:10-9:25 EDT: Project overview: Tasks, approaches, datasets and metrics. (Zhuo Chen)
  • 9:25-9:50 EDT: Target speaker extraction & recognition. (Desh Raj, Pavel Denisov, Katerina Zmolikova, and Marc Delcroix)
  • 9:50-10:12 EDT: Convolutional beamforming. (Christoph Boeddeke, Wangyou Zhang, and Tomohiro Nakatani)
  • 10:12-10:35 EDT: Target-speaker voice activity detection. (Maokui He, Yanhui Tu, Li Chai and Jun Du) 
  • 10:35-10:40 EDT: Stretch/Refreshment Break
  • 10:40-11:05 EDT: End to end neural diarization. (Zili Huang, Tobias Cord-Landwehr, Thilo von Neumann, Soumi , and Keisuke Kinoshita)
  • 11:05-11:30 EDT: Continuous speech separation for long recording processing. (Yi Luo, Cong Han, Chenda Li, Hakan Erdogan, and Zhuo Chen)
  • 11:30-11:45 EDT: Uncertainty modeling with application in diarization. (Anya Slinova, Johan Rohdin and Niko Brummer)
  • 11:45-12:00 EDT: Structured Output Learning for E2E-ASR Diarization. (Roshan Sharma and Shinji Watanabe) *

August 7: 9 AM-12:00 PM EDT Spoken Dialog Modeling and Evaluation Team Presentations


  • 9:00-9:20 EDT: Project overview: Tasks, approaches, datasets and metrics. (Alex Rudnicky and Markus Mueller)
  • 9:20-9:35 EDT: Exploration of End-to-End SLU Models (Xuandi Fu and Sahar Ghannay)
  • 9:35-9:50 EDT: End-to-End Models – Dealing with Dearth of Data. (Bhuvan Agrawal, Muqiao Yang, Roshan Sharma and Ian Lane)
  • 9:50-10:05 EDT: Beyond Utterances: Context-aware NLU with BERT. (Brandon Liang)
  • 10:05-10:10 EDT:  Stretch/Caffeine break
  • 10:10-10:25 EDT: Datasets preparation for training modern dialogue systems. (Mario Rodriguez-Cantelar, Luis Fernando D’Haro and Rafael Banchs)
  • 10:25-10:40 EDT: Reference-free Multi-dimensional Automatic Dialogue Evaluation. (Zhang Chen, Grandee Lee and Luis Fernando D’Haro)
  • 10:40-10:55 EDT: Learning to predict dialogue breakdown from turn transition probabilities in embedded spaces. (Andrew Koh and Rafael Banchs)
  • 10:55-11:10 EDT: Turn and dialogue level evaluation metrics for dialogue quality and AMT HIT designs. (Hugo Boulanger, Sam Davidson, Mario Rodriguez-Cantelar and Mathilde Veron)
  • 11:10-11:25 EDT: Collection of large-scale human-machine dialogue data for public release. (Sam Davidson and Anant Kaushik)
  • 11:25-11:30 EDT:  Stretch/Caffeine break
  • 11:30-11:45 EDT: Project summary and take-home messages. (Alex Rudnicky and Markus Mueller)
  • 11:50-12:00 EDT:  JSALT 2020 Concluding Remarks (Sanjeev Khudanpur)

Center for Language and Speech Processing