ECE 590SIP, Spring 2021


ECE 590SIP is a research seminar for people interested in speech and audio processing. Students may take it on a credit/no credit basis: credit is offered if you give a research presentation at least once during the semester. Students may attend without registering, and may give a presentation without registering. To schedule a talk, contact the instructor.

Presentation Schedule, Spring 2021

Wednesday, 1/27, 13:00-13:50
Mark Hasegawa-Johnson, Short descriptions of some papers that I recommend
Wednesday, 2/17, 13:00-13:50
No class; rest day!
Wednesday, 2/24, 13:00-13:50
John Harvill and Kiran Ramnath, Acoustic Word Embeddings.
Wednesday, 3/3, 13:00-13:50
Mahir Morshed
Heting Gao, Distributional robust optimization and invariant risk minimization for cross-lingual speech recognition
Wednesday, 3/10, 13:00-13:50
Efthymios Tzinis, Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
Wednesday, 3/17, 13:00-13:50
Shuju Shi, Automatic Prediction of Pronunciation Errors by Second Language Learners
Liming Wang, Multimodal Phone Discovery
Wednesday, 3/24, 13:00-13:50
No class; rest day!
Wednesday, 3/31, 13:00-13:50
Haozhong Guan
Junrui Ni: Regret Minimization applied to Cross-Lingual Speech Recognition
Wednesday, 4/7, 13:00-13:50
Jialu Li
Wednesday, 4/14, 13:00-13:50
Jamshed Kaikaus, Audiovisual emotion recognition
Wednesday, 4/21, 13:00-13:50
No class
Wednesday, 4/28, 13:00-13:50
Leda Sarı, Fairness in Artificial Intelligence
Wednesday, 5/5, 13:00-13:50
Yuchen Fan, Sparse Representation in Deep Vision Models