Jiachen Lian (连甲琛)

I am PhD Candidate at Berkeley EECS and I am affiliated at Berkeley Artificial Intelligence Research (BAIR) where I am advised by Prof. Gopala Krishna Anumanchipalli. I also collaborate closely with Prof. Maria Luisa Gorno Tempini to revolutionize language screening for children and deliver speech AI solutions to every individual with dyslexia and aphasia worldwide for both clinical and education efforts. I am also a Visiting Researhcer at Meta AI Seamless Team.

Email  |  Github  |  LinkedIn  |  Twitter  |  Facebook  |  Google Scholar

profile photo
Research

I’m interested in research questions that will still matter five years from now.

Currently, I work on the following areas:

(1) Human-Centered, Strong Supervised Learning Beyond Scaling Limits
Developing human-centric learning mechanisms and interactive labeling pipelines to extract strong supervision from imperfect and limited data. The goal is to enable intelligence-aware scaling—where learning is guided by insight, not just data volume.

(2) Modeling Human Verbal Behavior for Cognitive and Clinical Insights
Developing computational models to infer cognitive states from verbal behavior (e.g. dy(i)sfluency), focusing on voice-based biomarkers for speech and language disorders (e.g., Primary Progressive Aphasia, Dyslexia), and standardizing them for clinical integration.

(3) Condition-Specific AI for Diagnosis, Prevention, and Therapy
Designing precision-driven, condition-specific AI systems for early detection, risk prediction, and therapeutic support in speech and language disorders—aiming for clinical and educational deployment to support decision-making at both individual and population levels.

(4) Universal Language Function Evaluation at Scale
Building a unified platform for large-scale evaluation of language function across educational and clinical settings—combining pronunciation feedback, cognitive assessment, and other speech tasks in a synergistic framework. Also exploring HCI-driven service agents with accessible, interpretable, and socially aware interfaces to support longitudinal use.

Essay

Why do so few scientists make significant contributions and so many are forgotten in the long run [1]?
[1] https://www.cs.virginia.edu/~robins/YouAndYourResearch.pdf

News

Starting from 2025, as approved by the California State Government, public schools will adopt our language screener, where I developed the first and state-of-the-art speech dysfluency transcriber [UDM][SSDM], serving 1 million kids! See reports.


Selected Publications
Automated Lexical Dysfluency Analysis to Differentiate Primary Progressive Aphasia Variants
Jet M.J. Vonk* (co-first), Jiachen Lian* (co-first), Zoe Ezzes, Lisa Wauters, Cheol Jun Cho, Brittany T. Morin, Rian Bogley, Diana Rodriguez, Boon Lead Tee, Jessica DeLeon, Zachary Miller , Maria Luisa Mandelli, Gopala Krishna Anumanchipalli* (co-last), Maria Luisa Gorno-Tempini* (co-last)
AAIC (Alzheimer's Association International Conference) 2025 (Oral Presentation). AI Models can now Diagnose nfvPPA and lvPPA!
Automatic Detection of Articulatory-Based Disfluencies in Primary Progressive Aphasia
Jiachen Lian, Xuanru Zhou, Chenxu Guo, Zongli Ye, Zoe Ezzes, Jet Vonk, Brittany Morin, David Baquirin, Zachary Miller, Maria Luisa Gorno Tempini and Gopala Krishna Anumanchipalli,
2025 JSTSP An efficient AI Agent for Language Screening and Spoken Language Learning.
[Project Page]
SSDM: Scalable Speech Dysfluency Modeling
Jiachen Lian, Xuanru Zhou, Zoe Ezzes, Jet Vonk, Brittany Morin, David Baquirin, Zachary Miller, Maria Luisa Gorno Tempini and Gopala Krishna Anumanchipalli,
2024 NeurIPS. An AI Agent for Speech Therapy and Spoken Language Learning. A foundation model for scientific research, engineering deployment and business development .
[Project Page] ( NeurIPs Scholar Award )
Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection
Jiachen Lian, Carly Feng, Naasir Farooqi, Steve Li, Anshul Kashyap, Cheol Jun Cho, Peter Wu, Robbie Netzorg, Tingle Li, and Gopala Krishna Anumanchipalli,
2023 ASRU (Best Paper Nomination ). First work to detect both type and time of dys(dis)fluencies.
2024 Sevin Rosen Funds Award


Industrial
Meta AI, CA, USA
Visiting Researcher • Sep 2024 to Now
With: Seamless Team
Meta AI, CA, USA
Research Intern • July 2024 to Sep 2024
With: Vimal Manohar
Meta AI, CA, USA
FAIR-BAIR Student Researcher • Oct 2023 to May 2024
With: Wei-Ning Hsu
Meta AI, CA, USA
Research Intern • May 2022 to Dec. 2022
With: Alexei Baevski, Wei-Ning Hsu, Michael Auli
Speech and NLP Group, Tencent AI Lab(American) , WA, USA
Research Intern • Dec 2021 to Feb. 2022
With: Chunlei Zhang, Dong Yu
Speech and NLP Group, Tencent AI Lab(American) , WA, USA
Research Intern • April 2021 to Aug. 2021
With: Chunlei Zhang, Dong Yu
Teaching
Introduction to Robotics, Berkeley EECS , CA, USA
Reader • Fall 2024
Lab GSI.
Instructor: Prof. Roberto Horowitz
Audio Signal Processing in Humans and Machines, Berkeley EECS , CA, USA
Reader • Fall 2022
Instructor: Prof. Gopala Krishna Anumanchipalli
Introduction to Deep Learning, CMU LTI , PA, USA
Teaching Assistant • Fall 2020
Instructor: Prof. Bhiksha Raj
Education
UC Berkeley, U.S.
Ph.D. in EECS • Aug. 2021 to Present
Carnegie Mellon University, U.S.
M.S. in ECE • Sept.2019 to Dec. 2020
Zhejiang University, China
B.Eng. in EE • Aug. 2015 to June 2019

Awards
2024 NeurIPs Scholar Award
2024 Sevin Rosen Funds Award
2023 ASRU Best Paper Finalist
2021 Berkeley EECS Fellowship