Python codes for Lite Audio-Visual Speech Enhancement.

Related tags

Deep Learning LAVSE
Overview

Lite Audio-Visual Speech Enhancement (Interspeech 2020)

Introduction

This is the PyTorch implementation of Lite Audio-Visual Speech Enhancement (LAVSE).

We have also put some preprocessed sample data (including enhanced results) in this repository.

The dataset of TMSV (Taiwan Mandarin speech with video) used in LAVSE is released here.

Please cite the following paper if you find the codes useful in your research.

@inproceedings{chuang2020lite,
  title={Lite Audio-Visual Speech Enhancement},
  author={Chuang, Shang-Yi and Tsao, Yu and Lo, Chen-Chou and Wang, Hsin-Min},
  booktitle={Proc. Interspeech 2020}
}

Prerequisites

  • Ubuntu 18.04
  • Python 3.6
  • CUDA 10

You can use pip to install Python depedencies.

pip install -r requirements.txt

Usage

You can simply enter the command below and the average PESQ and STOI results will show on your terminal pane.

Remember to activate visdom (probably in a screen or tmux) for recording the training loss before bashing the script.

bash run.sh

Go check run.sh if you need further information about the command lines.

License

The LAVSE work is released under MIT License.

See LICENSE for more details.

Acknowledgments

  • Bio-ASP Lab, CITI, Academia Sinica, Taipei, Taiwan
  • SLAM Lab, IIS, Academia Sinica, Taipei, Taiwan
You might also like...
Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.
Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite.

TFLite-HITNET-Stereo-depth-estimation Python scripts form performing stereo depth estimation using the HITNET model in Tensorflow Lite. Stereo depth e

Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20. model in Tensorflow Lite.
Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20. model in Tensorflow Lite.

TFLite-msg_chn_wacv20-depth-completion Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20. model

Python scripts for performing stereo depth estimation using the MobileStereoNet model in Tensorflow Lite.
Python scripts for performing stereo depth estimation using the MobileStereoNet model in Tensorflow Lite.

TFLite-MobileStereoNet Python scripts for performing stereo depth estimation using the MobileStereoNet model in Tensorflow Lite. Stereo depth estimati

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation
BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation This is a demo implementation of BYOL for Audio (BYOL-A), a self-sup

This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.
This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

Lite-HRNet: A Lightweight High-Resolution Network Introduction This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution

A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!
A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!

A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

YOLOv5-Lite:lighter, faster and easier to deploy Perform a series of ablation experiments on yolov5 to make it lighter (smaller Flops, lower memory, a

Lite-HRNet: A Lightweight High-Resolution Network

LiteHRNet Benchmark 🔥 🔥 Based on MMsegmentation 🔥 🔥 Cityscapes FCN resize concat config mIoU last mAcc last eval last mIoU best mAcc best eval bes

Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.
Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.

TFlite Ultra Fast Lane Detection Inference Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite. So

Comments
  • preprocessed dataset?

    preprocessed dataset?

    I know we might need to download the Taiwan Mandarin Dataset, however, the preprocessed dataset in this repo. seems to be "wired"; any code to generate those files? especially the .pt ones.

    opened by wubinbai 1
  • Question about data shape on model output and target data

    Question about data shape on model output and target data

    Hi, I found that the shape of the model outputs (including audio and lip) do not contain frame_seq dimension. Under this condition, how does the loss be calculated due to the shape mismatch on model output and target data?

    opened by hsiaohan0827 1
Owner
Shang-Yi Chuang
Shang-Yi Chuang
A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering.

DeepFilterNet A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering. libDF contains Rust code used for dat

Hendrik Schröter 292 Dec 25, 2022
Facestar dataset. High quality audio-visual recordings of human conversational speech.

Facestar Dataset Description Existing audio-visual datasets for human speech are either captured in a clean, controlled environment but contain only a

Meta Research 87 Dec 21, 2022
PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

FullSubNet This Git repository for the official PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech E

郝翔 357 Jan 4, 2023
Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder

ASEGAN: Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder 中文版简介 Readme with English Version 介绍 基于SEGAN模型的改进版本,使用自主设计的非

Nitin 53 Nov 17, 2022
Implementation of "A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement" by pytorch

This repository is used to suspend the results of our paper "A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement"

ScorpioMiku 19 Sep 30, 2022
TCNN Temporal convolutional neural network for real-time speech enhancement in the time domain

TCNN Pandey A, Wang D L. TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain[C]//ICASSP 2019-2019 IEEE Int

凌逆战 16 Dec 30, 2022
The implementation of "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Band Speech Enhancement"

SF-Net for fullband SE This is the repo of the manuscript "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Ban

Guochen Yu 36 Dec 2, 2022
HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

HiFi++ : a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement This is the unofficial implementation of Vocoder part of

Rishikesh (ऋषिकेश) 118 Dec 29, 2022
Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models

Python scripts to detect faces using Python with the BlazeFace Tensorflow Lite models. Tested on Windows 10, Tensorflow 2.4.0 (Python 3.8).

Ibai Gorordo 46 Nov 17, 2022
Official codes for the paper "Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech"

ResDAVEnet-VQ Official PyTorch implementation of Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech What is in this repo? M

Wei-Ning Hsu 21 Aug 23, 2022