Giter Site home page Giter Site logo

zalolyricalignment's Introduction

Lyrics Alignment in ZALO AI 2022 Challenge 3

-- Project Status: [Active]

Overview

Problem statement

Many of us love to sing along with songs in the way of our favorite singers in albums (karaoke style). To make it, we may need to remove the vocals of the singer(s) from the songs, then provide the lyrics aligned timely with the accompaniment sounds. There are various tools to remove vocals, but it is hard to align the lyrics with the song.

In this challenge, participants will build a model to align lyrics with a music audio.

  • Input: a music segment (including vocal) and its lyrics.

  • Output: start-time and end-time of each word in the lyrics.

Evaluation

Accuracy

Accuracy of prediction will be evaluated using Intersection over Union (IoU). With IoU metric, the higher the better. The winner is the one achieving the highest IoU score.

image

IoU of prediction and the ground truth of an audio segment (๐‘ ๐‘–) is computed by the following formula:

image

With IoU metric, the higher the better. The winner is the one achieving the highest IoU score.

Datasets

Dataset is available here

Training data:

1057 music segments from ~ 480 songs.

Each segment is provided with an audio formatted as WAV file and a ground-truth JSON file which includes lyrics and aligned time frame of each single word as the above example.

Testing data:

Public test: 264 music segments from ~ 120 songs without aligned lyric files.

Private test: 464 music segments from ~ 200 songs without aligned lyric files.

Methods Used

  1. Use Spleeter/Demucs to extract voice from music
  2. Resampling audio to 16k (The default sampling rate)
  3. Fine-Tuning the pretrained model Wav2vec with CTC loss
  4. Force-alignment between audio and lyrics.
  5. Generate time-stamps of each word in lyrics

Usage

  • Using arguments:
    • --train : Training
    • --test : Testing
  • For Example (Testing): Run the Script:
    python main.py --test
    

Dataset

  • The complete Dataset is available here

Contact

zalolyricalignment's People

Contributors

boonichi avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

toperi-nguyen

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.