Skip to content
View jiangquewh's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Wuhan University
  • Wuhan, China
  • 19:47 (UTC -12:00)

Block or report jiangquewh

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
jiangquewh/README.md

🎙️ Jiang Que · 蒋雀

武汉大学研究生 · 声音克隆与表现力语音合成(TTS)大模型 · she/her


一句话概括我做的事:让机器不只是"像你"地说话,还能"有情绪、有节奏"地说话。

我从 多说话人音色克隆 起步——用少量样本迁移音色与韵律;再往前一步,研究 表现力语音合成:让情感、风格与韵律都可控。所有代码都能离线跑通:参考实现以纯 NumPy 为核心,import 不拉深度学习框架,无 GPU、无网络也能跑核心逻辑与单测;需要训练时再接可选的 PyTorch 后端。

📦 项目

timbrel — 多说话人声音克隆声学模型 说话人自适应 + 音色解耦,少样本克隆与韵律迁移,支持中英双语。

prosodia — 表现力语音合成大模型框架 情感 / 风格可控,接入语言模型做文本规范化与韵律预测,含流式与实时推理。

🧭 研究关键词

voice cloning · expressive TTS · prosody control · speaker adaptation · streaming inference · reproducible · offline-first


Wuhan University · 声音克隆 / 表现力 TTS · reproducible & offline-first

Pinned Loading

  1. prosodiaprosodiaPublic

    情感/风格可控的表现力语音合成框架:LLM 文本规范化与韵律预测,含流式实时推理(纯 Python,离线优先)

    Python

  2. timbreltimbrelPublic

    Bilingual multi-speaker voice-cloning acoustic model — timbre disentanglement, few-shot cloning, prosody transfer (zh/en)

    Python