Hi, I’m currently a third-year PhD student at the Language Technologies Institute of the School of Computer Science at Carnegie Mellon University, advised by Prof. Lei Li. Before I came to CMU, I spent two years as a PhD student at the Computer Science Department at UC Santa Barbara also with Lei. Before PhD, I received my B.Eng. from the Institute for Interdisciplinary Information Sciences at Tsinghua University (a.k.a. Yao Class), advised by Prof. Yi Wu.
My current research focus is on low-latency simultaneous speech translation with a large language model. The ambition is to build a system that can translate speech in real time (less than one-second latency), enabling face-to-face communication for people speaking different languages.
‣ Twitter/X
‣ Linkedin
‣ Github
‣ Scholar
Updates
Selected Publications
- Anticipating Future with Large Language Model for Simultaneous Machine Translation
Siqi Ouyang, Oleksii Hrinchuk, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Lei Li, Boris Ginsburg
Preprint 2024
[paper]
- CA: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation*
Xi Xu, Wenda Xu, Siqi Ouyang, Lei Li
Preprint 2024
[paper]
- FASST: Fast LLM-based Simultaneous Speech Translation
Siqi Ouyang, Xi Xu, Chinmay Dandekar, Lei Li
Preprint 2024
[paper]
- CMU's IWSLT 2024 Simultaneous Speech Translation System
Xi Xu, Siqi Ouyang, Brian Yan, Patrick Fernandes, William Chen, Lei Li, Graham Neubig, Shinji Watanabe
IWSLT 2024, Top 1 Human Rating
[paper]
- WACO: Word-aligned contrastive learning for speech translation
Siqi Ouyang, Rong Ye, Lei Li
ACL 2023
[paper] [code] [blog]
- On the impact of noises in crowd-sourced data for speech translation
Siqi Ouyang, Rong Ye, Lei Li
IWSLT 2022
[paper] [code]
Selected Awards
- Waibel Presidential Fellowship 2024
- Tsinghua University Yao Recognition Prize 2021
- Gold Medal, Chinese National Olympiad in Informatics 2016
Contact
Email: siqiouya[at]andrew.cmu.edu