pytorch / pytorch/audio

Add MFCC inverse to waveform

Open
#2,920 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.9k
Forks
799
Avg merge
58m
Merged PRs (30d)
3

Description

🚀 The feature

recover waveform from MFCC like librosa.feature.inverse.mfcc_to_audio function

Motivation, pitch

I am working a problem about speech synthesis and I use librosa.feature.inverse.mfcc_to_audio to recover waveform from MFCC, but librosa's function cost too much CPU calculation and I want to use torchaudio and GPU to accelerate it.
And if there is a function can recover waveform from MFCC, I can use it in my deep learning training and calculate synthesis loss from deep learning model.

Alternatives

librosa.feature.inverse.mfcc_to_audio to recover waveform from MFCC
but it cost CPU and can not use in deep learning training

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by comparing the requested behavior with librosa.feature.inverse.mfcc_to_audio and review the repository's existing audio transforms and GPU-compatible signal-processing entry points. Done means providing an MFCC-to-waveform operation usable with PyTorch tensors and GPU-backed training, with behavior validated against the librosa alternative; the issue names no repository files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
audio-video-rtc, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.