Mengjie Qian 钱梦洁

Research Associate, University of Cambridge

I am a Research Associate in the Machine Intelligence Laboratory at the University of Cambridge, working with Prof. Kate Knill and Prof. Mark Gales.

My research focuses on speech foundation models (SFMs) and large language models (LLMs), particularly their application in education and healthcare for low-resource languages.

Speech Foundation Models LLMs Spoken Language Assessment Healthcare AI

Latest Highlights

Apr 2026 M. Qian, G. Sun, M. Gales, K. Knill, “Who can we trust? LLM-as-a-jury for Comparative Assessment”, ICML 2026 (accepted).

Mar 2026 Co‑applicant (one of two), Cambridge Language Sciences Incubator Fund Award: “The phonetics and phonology of Llanito, Gibraltar‘s dying language” (£5,994.00).

Dec 2025 Awarded Cambridge Language Sciences Incubator Fund for research on Alzheimer’s Dementia detection (£7.5k).

2025 Lead Organiser of the Speak & Improve Challenge 2025.

Education

Ph.D. in Engineering 2016 – 2021

University of Birmingham, UK

Thesis: “Computer Analysis of Children’s Non-Native English Speech for Language Learning and Assessment”
Supervisors: Prof. Martin Russell, Dr. Peter Jančovič.

B.S. in Electronic Engineering 2010 – 2014

University of Science and Technology of China (USTC)

Supervisor: Prof. Ian McLoughlin.

Grants & Funding

Co‑applicant (one of two), Cambridge Language Sciences Incubator Fund Award: “The phonetics and phonology of Llanito, Gibraltar‘s dying language” (Mar 2026)
Lead Applicant, Cambridge Language Sciences Incubator Fund Award: “Beyond Accuracy: Confidence-Aware Speech Models for Alzheimer’s Detection” (Dec 2025).
Co-Applicant, Cambridge Language Sciences Incubator Fund Award: “Hearing Every Voice: Interpretable Voice Quality Labelling for Inclusive AI” (Dec 2025).
Co-Applicant, Cambridge Language Sciences Incubator Fund proposal: “The phonetics and phonology of Llanito, Gibraltar’s dying language” (Submitted Jan 2026).

Invited Talks

2025

Universal Acoustic Adversarial Attacks: From Muting to Controlling Speech Foundation and Language Models Nove 2025; University of Science and Technology of China, China

From Challenge to Solution: Speak & Improve Challenge 2025 and Advances in End-to-End Spoken Grammatical Error Correction Sep 2025; ISCA SIGML Seminar

2024

Automated Learning Teaching and Assessment: Spoken Language Processing Technology Project June 2024; Second Language Acquisition with Speech and Language Technologies (SLASaLT) Workshop, University of Sheffield