Speech and Language Technologies (SALT) Frontiers Lecture Series

The Department of Electronic Engineering at Tsinghua University launched the Speech and Language Technologies (SALT) Frontiers Lecture Series. The aim of this initiative is to promote sustainable academic communications and interactions. Speech and language technologies cover highly important and active areas of research, and the Department has a long and accomplished history in these fields. The lecture series invites distinguished researchers worldwide, from both academia and industry, to present cutting-edge vision, ideas, and research outcomes.
After the COVID-19 pandemic, the lecture series has been expanded to incorporate SALT seminars with evolving topics, such as SALT-Semi and SALT-Multilingual. The venues are no longer limited to the Department of Electronic Engineering; by organizing activities in different cities and institutions, the series strengthens broader engagement and interaction with the speech and language technology community.
All lectures and seminars are open and free to the public. With the speakers' permission, the lectures and seminars will be recorded and distributed through the Department website and related media.
This website serves as an information hub for the lecture series and related seminars. We welcome your participation in the THUEE-SALT Frontiers Lecture Series.

Schedule

Time and Venue Speaker and Lecture-Title Chair
Mar. 25, 2022
10:00-11:00 AM
Zoom: 934 1318 5672
What's Next in Learning for Audio – Going past chasing metrics
Paris Smaragdis, University of Illinois at Urbana-Champaign
youtube | bilibili
 Zhijian Ou
(Tsinghua University)
May 31, 2023
10:00-11:00 AM
Tencent Meeting: 337-287-336
Learning to Disentangle Speech Information
Yang Zhang, MIT-IBM Watson AI Lab
slides | youtube | bilibili
 Zhijian Ou
(Tsinghua University)
Sep. 23, 2023
Nanning, China
The 1st Seminar on Multilingual Speech and Language AI Technologies (SALT-Multilingual)
Speech Generation Mechanism and Multilingual Intelligent Speech Processing
Jianwu Dang, Tianjin University
Language, Intelligence, Future
Cairangjia, Qinghai Normal University
Multilingual Explainable Voiceprint Recognition
Liang He, Xinjiang University
Yao Language Phonological Structure and Sound Change Rules
Meihua Pan, Guangxi University for Nationalities
Use and Protection of Zhuang Language and Script
Sheng Lan, Guangxi University for Nationalities
 Donghong Qin
(Guangxi University for Nationalities)

Zhijian Ou
(Tsinghua University)
Dec. 9, 2023
Suzhou, China
The 1st Seminar on Semi-Supervised Speech and Language AI Technologies (SALT-Semi), Co-located with NCMMSC 2023
Reflections on Semi-Supervised Learning Paradigms in Speech Recognition
Yonghong Yan, Institute of Acoustics, Chinese Academy of Sciences
Large-Scale Foundation Model for Speech Generation
Wei-Ning Hsu, Meta
Exploring the Domain of Large-Scale Language Models—Taking Legal Scenarios as an Example
Yansong Feng, Peking University
Zero-Shot Cross-Language Speech Synthesis and Translation
Shujie Liu, Microsoft Research Asia
 Zhijian Ou
(Tsinghua University)

Pengyuan Zhang
(Institute of Acoustics, Chinese Academy of Sciences)
Aug. 16, 2024
Urumqi, China
The 2nd Seminar on Multilingual Speech and Language AI Technologies (2nd SALT-Multilingual), Co-located with NCMMSC 2024
 Hao Huang
(Xinjiang University)

Zhijian Ou
(Tsinghua University)
Oct. 18, 2025
Zhenjiang, China
The 2nd Seminar on Semi-Supervised Speech and Language AI Technologies (2nd SALT-Semi), Co-located with NCMMSC 2025
Retrieval-Augmented Speech Recognition and the Development of Challenging Speech Tasks
Yong Qin, Nankai University
Recent Advances in Machine Voiceprint for Robust Machine Anomalous Sound Detection
Yanmin Qian, Shanghai Jiao Tong University
Speaker Recognition Based on Self-Supervised Learning
Ming Li, Duke Kunshan University
Towards Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric and Elderly Speech Recognition
Xunying Liu, The Chinese University of Hong Kong
Phonemes as Speech-Language Interface for Data-Efficient Multilingual and Crosslingual Speech Recognition
Zhijian Ou, Tsinghua University
 Pengyuan Zhang
(Institute of Acoustics, Chinese Academy of Sciences)

Zhijian Ou
(Tsinghua University)

Copyright © 2022 Department of Electronic Engineering, Tsinghua University. All Rights Reserved.