Skip to content
View isla-brooks's full-sized avatar
🏠
Working from home
🏠
Working from home
  • Nanjing University
  • Nanjing, China

Block or report isla-brooks

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.

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
isla-brooks/README.md

Han Xiaoyu · 韩晓雨

南京大学研究生 · 声音大模型 —— 听懂声音,也生成声音。

我在研究什么? 两件事:让模型 听懂 环境声音(场景、事件),也让它 生成 声音(音效、环境声)。一进一出,都围绕「声音」这件事做大模型。

做过什么?

听懂soundscape-lm 声学场景分类 + 声音事件检测,接入大语言模型做场景描述与音频–文本检索。

生成foley-flow 文本 / 条件驱动的音效(Foley)与环境声生成,扩散 / 流匹配声学模型,含时序对齐。

怎么写代码? numpy / scipy 内核,import 不拉深度学习框架;无 GPU、无网络也能跑核心与单测;需要训练时再接可选 PyTorch。离线优先,CI 全绿。

Nanjing University · 声音大模型 · 听懂 + 生成 · she/her

Pinned Loading

  1. foley-flow foley-flow Public

    可控 Foley / 环境声生成框架:文本与时序条件驱动,扩散与流匹配声学模型,Griffin-Lim 声码器,纯 numpy/scipy、离线优先

    Python 1

  2. soundscape-lm soundscape-lm Public

    环境声音理解工具包:声学场景分类 + 声音事件检测,接入大模型做场景描述与音频-文本检索(numpy/scipy 核心,离线优先)

    Python 1

  3. ruxinliang-dev/groomist ruxinliang-dev/groomist Public

    One-click Ornatrix groom builder for Maya - setup, operator stack, performance toggles, handoff helpers. Single-file, MIT.

    Python 24 4

  4. ufy2024/AuC ufy2024/AuC Public

    Agents-ufy-Core

    Python 695 28