ECE 590SIC, Spring 2023


Purpose of the course
ECE 590SIC is a research seminar for people interested in audio, speech and language processing.
Grad students may take ECE 590SIC for one unit of graduate credit. Grades are S/U/I. An "S" grade is given if you either: (1) give a research presentation at least once during the semester, or (2) participate in a group project and submit some kind of report, co-authored with your group, describing your experimental results, or (3) submit a written report describing the presentations given by visiting speakers. Students may also attend without registering, and may give a presentation without registering.
Mark Hasegawa-Johnson.
Seminar Locations and Dates
The course is held Wednesdays, 4-5pm in ECEB 2017. Every class is hybrid; the zoom link is on the CampusWire at

Course Schedule, Spring 2023

Wednesday, 1/18, 4pm
Small-group project planning: nominate ideas for small-group projects, and create a document sketching the ideas.
Wednesday, 1/25, 4pm
Small-group project planning.
Wednesday, 2/1, 4pm
Mark Hasegawa-Johnson, Zipf's law suggests a three-pronged approach to inclusive speech recognition
Wednesday, 2/8, 4pm
Zhongweiyang Xu, Real World Neural Speech Enhancement, Separation, and Dereverberation for Monaural, Multichannel, and Multi-modal Setup
Wednesday, 2/15, 4pm
No class
Wednesday, 2/22, 3:30pm
Ajay Divakaran will speak to the NLP group at this time. Title: Using Hierarchies of Skills to Assess and Achieve Automatic Multimodal Comprehension
Monday, 2/27, 3:30pm
Graham Neubig will speak to the NLP group at this time. Title: Is My NLP Model Working? The Answer is Harder Than You Think.
Wednesday, 3/1, 5pm
G2P/homograph discovery (John, Mahir, Heting, Xiuwen)
Vision-speech navigation (Liming, Feiyu, Debottam)
Wednesday, 3/8, 4pm
Fairness in speech recognition (Erin, Priyam, Steven)
Audio captioning (Xulin)
Wednesday, 3/15, 4pm
No class; Spring break
Wednesday, 3/22, 4pm
Mahir Morshed, Direct Exposure of Speech Articulations in Model Architectures for Downstream Processing
Wednesday, 3/29, 4pm
Eunice Opoku and Katya Yegorova, The Structure of Motion Predicates in Akan
Thursday, 3/30, 4:30-5:30pm, 3017 ECEB
David Harwath, Learning Speech Audio Representations with Multimodal Self-Supervision
Wednesday, 4/5, 4pm
Jialu Li, Towards Automatic Understanding of Parent-Child Interaction Patterns from Family Audio to Monitor Child Mental Health
Monday, 4/10, 9:00-10:00am, B02 CSL
Lianhui Qin, Constrained, Causal, and Logical Reasoning for Neural Language Generation
Wednesday, 4/19, 4pm
Liming Wang
Wednesday, 4/26, 4pm
No Class
Wednesday, 5/3, 4pm
Final project presentations:
  • Fairness
  • Vision-speech navigation
  • Audio captioning