Skip to content
View olong75's full-sized avatar
🤒
Out sick
🤒
Out sick
2 followers · 3 following
  • Communication University of China
  • Beijing, China

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report olong75

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
olong75/README.md

Fang Zhiyuan

CUC · I clean up broken audio — noise, reverb, clipping, dropouts, and echo.

the problem the tool
noisy / reverberant / clipped / gapped speech revoice
echo & double-talk on a live call echoquell
  • revoice — speech restoration: denoising, dereverberation, declipping, and packet-loss concealment, with PESQ / STOI-style evaluation.
  • echoquell — acoustic echo cancellation: adaptive NLMS / RLS filtering + residual echo suppression, with double-talk detection and ERLE evaluation.

NumPy core, optional PyTorch backend — offline-first, CI green.

Pinned Loading

  1. echoquell echoquell Public

    an acoustic echo cancellation (AEC) toolkit in Python: adaptive filtering (NLMS/RLS) + residual echo suppression for teleconferencing, with double-talk detection and evaluation (ERLE), pure-Python …

    Python 3

  2. revoice revoice Public

    a speech restoration toolkit in Python: single-channel denoising, dereverberation, declipping, and packet-loss concealment with objective evaluation (PESQ/STOI-style), NumPy core with an optional P…

    Python 2