ECE 590SIC: Graduate Seminar in Speech, Spring 2024¶
This is a one-hour graduate seminar on topics of speech processing.
Meeting Time, Date, Place, and Discussion¶
Day and time: Wednesdays, 4:00-4:50pm.
Place: ECEB 2017.
Discussion: CampusWire.
Expected Participation¶
For now, the class has been divided into three groups:
Group 1: Heting, Priyam, Xulin, Mahir, Kamila
Group 2: Junrui, Jeff, Bornali, Xiuwen, John
Group 3: Haolong, Zhongweiyang, Katya, Steven, Jocelyn
For your week, please choose an article, and let me know what it is! Some possibilities that have been recommended are:
Please also consider any of the references cited in the first three weeks, any of the papers that cite one of the papers in the first three weeks, or anything from Interspeech 2023.
Weekly Schedule¶
Week |
Date |
Topic |
|---|---|---|
1 |
17-Jan |
No Class |
2 |
24-Jan |
DiarizationLM: Speaker Diarization Post-Processing with Large Language Models |
3 |
31-Jan |
Grad-TTS: A diffusion probabilistic model for text-to-speech |
4 |
7-Feb |
Reproducing Whisper-Style Training Using An Open-Source Toolkit And Publicly Available Data |
5 |
14-Feb |
Group 1: Accented Speech Recognition with Accent-specific Codebooks (slides) |
6 |
21-Feb |
|
7 |
28-Feb |
|
8 |
6-Mar |
Group 3: Accentron: Foreign accent conversion to arbitrary non-native speakers using zero-shot learning (slides) |
9 |
13-Mar |
Spring Break |
10 |
20-Mar |
No Class |
11 |
27-Mar |
Group 1: Sora: A Review on Background Technology Limitations and Opportunities of Large Vision Models (slides) |
12 |
3-Apr |
|
13 |
10-Apr |
Group 3: SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (slides) |
14 |
17-Apr |
No Class |
15 |
24-Apr |
Discuss mechanics of a poster session |
16 |
1-May |
Poster session |
