ECE 590SIP, Fall 2020

Image Source


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, Fall 2020

Monday 9/14, 16:00-16:50
Saurabchand Bhati: Self-expressing autoencoders for unsupervised feature learning
Monday 9/21, 16:00-16:50
Leda Sari: Deep F-measure Maximization for End-to-End Speech Understanding
Siyuan Feng: Unsupervised Subword Modeling Using Autoregressive Pretraining and Cross-Lingual Phone-Aware Modeling
Monday 9/28, 16:00-16:50
Ali Abavisani: Automatic Estimation of Inteligibility Measure for Consonants in Speech
Jialu Li. Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?
Monday 10/5, 16:00-16:50
Aamir Hassan: It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
Monday 10/12, 16:00-16:50
Heting Gao: Equal Accuracy Ratio for Fair Speech Recognition
Monday 10/19, 16:00-16:50
John Harvill: Improving recognition for dysarthric speech
Monday 10/26, 16:00-16:50
Mahir Morshed: An Overview of Methods for Articulatory Feature Detection
Monday 11/2, 16:00-16:50
Xinsheng Wang: An overview of speech-visual multimodal learning
Monday 11/9, 16:00-16:50
Jamshed Kaikaus: Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
Monday 11/16, 16:00-16:50
Liming Wang: Align or attend? Toward more efficient and accurate spoken word discovery using speech-to-image retrieval
Monday 11/30, 16:00-16:50
Haozhong Guan
Monday 12/7, 16:00-16:50
Shuju Shi: Vowel inventories in Mandarin and English and the implications on L1 Chinese L2 English acquisition
Razan Baltaji: Back Translation for Semitic Root Extraction