Skip to content
View hazelp343's full-sized avatar
  • Zhejiang University
  • Hangzhou, China

Block or report hazelp343

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
hazelp343/README.md

杨明言 (Mingyan Yang)

Graduate student working on sound and audio foundation models. I build small, readable, open-source tooling for the audio stack — general-purpose embeddings, sound-event detection, text-to-audio generation, and audio question-answering with LLMs — with a bias toward code that is reproducible and offline-by-default: minimal dependencies, no checkpoints to download, and pipelines that run end-to-end on a CPU.

The thread running through my projects is that you should be able to read the machinery. Most audio repositories are either thin FFT wrappers or research dumps wired to multi-gigabyte deep-learning stacks. I aim for the middle — batteries-included but lightweight enough to understand in an afternoon.


🔬 Research interests

  • General-purpose audio representations — embeddings for retrieval, clustering, and similarity.
  • Sound-event detection — frame-level detection with honest, literature- aligned evaluation (segment- and event-based metrics, collars and all).
  • Text-to-audio / foley generation — latent diffusion for sound effects.
  • Audio question-answering with large language models — connecting audio representations to LLMs for reasoning over sound.

📦 Featured projects

Project What it is Stack
resona Lightweight, NumPy-first toolkit for audio embeddings and sound-event detection: STFT / mel / MFCC / spectral features, three pluggable embedders, threshold + energy-gate detectors, and segment- and event-based metrics — one dependency, runs anywhere Python does. Python · NumPy
foleydiff Compact latent-diffusion toolkit for text-to-audio and sound-effect (foley) generation in plain PyTorch: a mel-spectrogram VAE, a conditional 1-D U-Net, DDPM/DDIM samplers with classifier-free guidance, and a Griffin-Lim vocoder — the whole stack from scratch, no pretrained weights required. Python · PyTorch
harken Small PyTorch framework that connects a frozen audio encoder to an LLM for audio question answering: pluggable encoders (CLAP / Whisper / AST), a projector zoo (linear / MLP / temporal-stack / Q-Former-style), LLaVA-style token splicing, and abstention-aware evaluation — with a download-free core that runs the full pipeline on CPU. Python · PyTorch

Each project is MIT-licensed, typed, linted, and tested across recent CPython versions, and ships synthetic data so the full pipeline runs with no external downloads.


🧰 Tooling

Python NumPy PyTorch ruff mypy pytest License: MIT


🛠️ Currently

Tying the three pieces together: better audio representations feeding both sound-event detection and audio question-answering, while keeping the constraints that shape everything above — minimal dependencies, reproducible runs, and components small enough to read.

📍 Seattle, WA · open-source, reproducible audio research tooling.

Pinned Loading

  1. foleydiff foleydiff Public

    Compact PyTorch latent-diffusion toolkit for text-to-audio and sound-effect (foley) generation

    Python 1

  2. harken harken Public

    A small PyTorch framework that connects pretrained audio encoders to LLMs for audio question answering

    Python 1

  3. resona resona Public

    Lightweight, NumPy-first toolkit for audio embeddings and sound-event detection

    Python 1

  4. Kail-Fu/InterviewOS Kail-Fu/InterviewOS Public

    Replace coding puzzles with real-work simulations.

    Python 1.9k 148