CV

Langchu Huang

12213009@mail.sustech.edu.cn
Shenzhen, Guangdong, CN

Education

  • B.E. in Computer Science and Technology
    2022.09 — 2026.06
    College of Engineering, Southern University of Science and Technology (SUSTech)
    GPA: 3.8 / 4.0
    Advisor: Prof. Yang Xu
    Selected Courses: NLP (A+), ML (A), DL (A-), AI (A-)
    Research Interest: Music Information Retrieval, Natural Language Processing, Signal Processing
  • Non-degree in Exchange Program
    2025.09 — 2025.12
    School of Engineering, Hong Kong University of Science and Technology (HKUST)
    Selected Courses: Music Theory, Composition, Signal Processing

Experience

  • Undergraduate Research
    2024.09 — 2025.12
    College of Engineering, Southern University of Science and Technology
    Exploring the impact of paralinguistic signals in dialogue datasets on language model performance across tasks.
  • Research Assistant
    2025.07 — 2025.08
    Department of Electrical and Computer Engineering, North Carolina State University
    Conducted research in the ARoS Lab under Prof. Lobaton. Designed a data collection protocol and built a dual-modal cough-speech dataset using both air and bone conduction. Developed a dual-path contrastive learning architecture for robust cough-speech detection.
  • Visiting Research Student
    2025.09 — 2025.12
    School of Engineering, Hong Kong University of Science and Technology
    Developing a multitrack symbolic music codec for LMs, aiming to design compact discrete representations to enhance symbolic music understanding and generation. The work explores residual vector quantization, interleaved ABC notation, and multimodal alignment for controllable, musically coherent outputs.
  • Research Intern
    2025.11 — 2026.03
    Lyra Lab, Tencent Music Entertainment
    Developed a lyric-aware symbolic music foundation model with attribute-wise masked pretraining and hybrid music–language embeddings, improving vocal-centric understanding while maintaining strong performance on symbolic music classification benchmarks. Also developing a symbolic music generation algorithm that transforms lead sheets into full piano arrangements by modeling harmonic realization, voicing structure, and accompaniment texture.

Publications

  • Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models
    2025
    preprint
    Authors: Yu Wang, Leyi Lao, Langchu Huang, Gabriel Skantze, Yang Xu, Hendrik Buschmeier
    This work investigates how fine-tuning strategies enhance language models’ ability to represent and generate backchannels and fillers in dialogue. Empirical analyses demonstrate improved clustering quality and more human-like language generation, showcasing the potential for adapting general LMs into pragmatic-aware conversational models.
  • LyricMidi: Joint Music–Language Pretraining for Symbolic Music Understanding
    2026
    ICME under review
    Authors: Langchu Huang, Yiliang Jiang, Ying Chen, Lingcheng Kong, Weifeng Zhao
    This paper proposes a unified music–language pretraining framework that jointly models symbolic music events and lyrics. The model achieves consistent improvements on vocal-centric symbolic music understanding tasks while preserving general music representation performance.

Awards

  • Academic Scholarship, SUSTech
    2022, 2023, 2024
  • Outstanding Student Award, SUSTech
    2022, 2023, 2024
  • First Prize, 7th National Student Art Exhibition, for Mahler Piano Quartet in A Minor
    2023
  • Second Prize, Chamber Music (Non-Major Division), 3rd GBA College Student Art Festival
    2024
  • Second Prize, China Undergraduate Mathematical Contest in Modeling
    2023

Certificates

  • TOEFL (MyBest)
    100 (R 25, L 27, S 23, W 25)
  • GRE
    317 (V 152, Q 165)

Portfolio

  • Chamber Music Performance – Gustav Mahler: Piano Quartet in A Minor
    2024
    Chamber music performance as pianist in Gustav Mahler’s Piano Quartet in A Minor.
  • SVSMate – The Ultimate VSCode Extension for SUSTechers
    2025
    Integrate Blackboard academic services into VS Code developer workflows.
  • ABCD: Air-Bone Cough Contrastive Detector for Dual-Path Edge Audio Health Monitoring
    2025
    A dual-path health monitoring system using both air conduction and bone conduction audio signal. Developed during internship at NCSU ECE.

Skills

  • Programming : Python, C++, TypeScript, LaTeX, Lua
  • Music : Piano, Chamber Music Performance, Music Theory and Notation, Basic Composition

Languages

Cantonese (native), Mandarin (native), English (fluent)

Teaching

  • Acoustics and Music Teaching for Rural Children
    2023.07
    Volunteer Teacher in Lianping Teaching Support Program, providing introductory acoustics and music lessons to rural primary school students
  • Volunteer Guide and Interpreter
    2025.06
    University of San Francisco Shenzhen Summer Program
  • Piano and Music Theory Tutoring
    2024, 2025
    Provided individualized private instruction to children and adolescents for 2 years, focusing on fundamental to intermediate performance skills and music literacy

Leadership

  • President, MovieSalon Club
    2023.07 - 2024.07
    SUSTech
  • President, Camerata Coffee Club
    2023.07 - 2024.07
    SUSTech