Technical Program
Time Slots (IST) | 12th Aug | 13th Aug |
---|---|---|
10.00-10.30 | Inauguration | Title: Speech Processing - Handcrafted features to Deep Representations Speaker: Mahadeva Prasanna, IIT Dharwad Slides Video |
10.30-11.00 | Title: Overview of Speech Recognition Technology in Conversational Agents Speaker: Sri Garimella, Amazon |
|
11.00-11.30 | ||
11.30-12.00 | Title: Spoken Language Understanding for the Indic Region Speaker: Anurag Dwarakanath, Amazon Slides Video |
|
12.00-12.30 | ||
12.30-12.45 | Sponsor Talk - IndSCA | Break |
12.45-13.00 | Sponsor Talk - Gnani.ai | |
13.00-13.15 | Sponsor Talk - NavanaTech | Title: Automatic Speech Recognition using Models from GMM-HMM to Transformers to wav2vec2.0 Speaker: S Umesh, IIT Madras Video |
13.15-13.30 | Sponsor Talk - MSR India | |
13.30-14.00 | BREAK | |
14.00-14.30 | Panel Discussion: Multilingual and code-switching ASR in Indian Language - Present & Future | |
14.30-15.00 | ||
15:00-15:15 | Introduction to Challenge by Chiranjeevi Yarra, IIIT Hyderabad Slides Video |
|
15:15-15:30 | ||
15:30-15:45 | Team: CSTR Slides Video |
Break |
15:45-16:00 | Team: Bytedance-SA Slides Video |
|
16:00-16:15 | Team: Ekstep Slides Video |
Title: Recent advances in transfer learning and multilingual methods for streaming end-to-end ASR systems Speaker: Vikas Joshi, Microsoft Slides Video |
16:15-16:30 | Team: GOT-HIM Slides Video |
|
16:30-16:45 | Team: GoVivace Slides Video |
|
16:45-17:00 | Team: Sayint Slides Video |
|
17:00-17:15 | Team: Dialpad Slides Video |
Title: Introduction of ESPnet, End-to-End Speech Processing Toolkit Speaker: Shinji Watanabe, Carnegie Mellon University & Pengcheng Guo, Northwestern Polytechnical University & Sathvik Udupa, IIsc Bangalore Slides Video |
17:15-17:30 | Team: JHU-CLSP/GoVivace Slides Video |
|
17:30-17:45 | Team: IITM-SMT-Lab Slides Video |
|
17:45-18:00 | Conclusion to the Challenge | |
18:00-18:15 | Winner Announcement | |
18:15-18:30 | Break | |
18.30-19.00 | Title: What next after ASR in Indian Languages? We speak in order to be understood! Speaker: Samuel Thomas, IBM T.J. Watson Research Center, New York Slides Video |
|
19.00-19.30 | ||
19.30-20.00 | Closing session and Vote of Thanks |