Hi, I'm

Turi Abu

PhD Student in Computer Science · Tsinghua University

I recently started my PhD in Computer Science at Tsinghua University. I am conducting research at the Center for Speech and Language Technologies (CSLT), co-supervised by Prof. Thomas Fang Zheng (Tsinghua University) and Cheng Feng (Siemens Company). My current work focuses on Visual Speech Recognition, and my broader interests span speech and language technologies, including ASR, multimodal speech understanding, and NLP.
CV
Turi Abu
01

News

  1. December 21, 2024

    🎉Paper accepted at ICASSP 2025 Conference

    Our research paper 'Sagalee: An Open Source Automatic Speech Recognition Dataset for Oromo Langauge' has been accepted for presentation at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025)

  2. June 25, 2023

    【毕业季】学校举行2023届优秀毕业生代表座谈会

    School held the 2023 Symposium of Outstanding Graduate Representatives

  3. December 6, 2022

    Three International Students Awarded the Title: 2022 Excellent International Students of UESTC

    Recipient of the 2022 Excellent International Students of UESTC award

02

Publications

A Framework for Identity Verification Based on Fusion of Voice and Face With Incomplete Information
APSIPA Transactions on Signal and Information Processing2026

A Framework for Identity Verification Based on Fusion of Voice and Face With Incomplete Information

Juntao Wang, Xiaolong Wu, Mingxing Xu, Turi Abu, Askar Hamdulla & Thomas Fang Zheng

03

Experience

  1. June 2026 - August 2026

    Intern AI Engineer · Z.ai

    Worked on AutoClaw and Zwork, AI agent harnesses that can complete long horizon tasks helping people complete their work.

  2. September 2025 - Present

    Research Assistant · CSLT, Tsinghua University

    Advisor: Prof. Thomas Fang Zheng

    Focus: Visual Speech Recognition, learning the relationship between lip movement and transcript.

    • Masters Work (December 2023 - June 2025): Speech recognition for low resource languages. Created a speech recognition dataset and open sourced it.

  3. October 2022 - March 2023

    Intern-AI Engineer · Hongchengyun Technology Co., Ltd (HCYTech)

    • Smoke Detection: trained a cigarette smoking detection model using YOLO and built a smoking detection API.
    • Speech Recognition: built an API for speech recognition using the open source Whisper model.
04

Education

  1. 2025—Present

    Tsinghua University

    PhD in Computer Science

    Advisor: Prof. Thomas Fang Zheng (Tsinghua University) & Cheng Feng (Siemens Company)

  2. 2023—2025

    Tsinghua University

    MSc in Computer Science

  3. 2019—2023

    University of Electronic Science and Technology of China

    BSc in Software Engineering

05

Projects

Mobile Application for Speech Data Collection

Mobile Application for Speech Data Collection

  • Developed android application for Automatic Speech Recognition data colllection using Flutter and firebase
FlutterFirebaseAndroid
Code
Local Retrieval Augmented Generation (RAG) Using Ollama

Local Retrieval Augmented Generation (RAG) Using Ollama

  • Built a local RAG using open source llama model for question answering task
DockerOllamaFlaskRAG
Code
Finetuning LLM for Grammatical Error Correction (GEC)

Finetuning LLM for Grammatical Error Correction (GEC)

  • Fine-tuned T5 Flan-based model on JFLEG dataset for GEC task, and built Grammarly like website for demo
PythonPyTorchFlaskReactLLM
Code
CodeDig - Semantic Code Search Engine

CodeDig - Semantic Code Search Engine

  • Built a semantic code search engine using ChatGLM API, whoosh library, and Flask.
PythonLLMflaskDocument indexing
Code
Distributed Database Management System

Distributed Database Management System

  • Design and implementation of Distributed database system.
PythonMinIOMySQLFlask
Code