AMT-APC: AMT-APC: Automatic Piano Cover by Fine-Tuning an Automatic Music Transcription Model

NOMAD: Non-Matching Audio Distance (ICASSP 2024)

PiCoGen (Piano Cover Generation) is an academic project aimed at developing an automatic piano cover generation system.

This is the implementation of a LSTM Recurrent Neural Network that composes a melody to a given chord sequence.

ChatTTS 2000条音色稳定性打分🥇+区分男女年龄👧+在线试听🔈 ChatTTS 2K Speaker Stability Score & Categorized by Gender and Age & Audio Preview

SOFA: Singing-Oriented Forced Aligner

Two-vocal Separation and Singing Pitch Transcription

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Code for ISMIR 2020 paper: "Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks"

Code for ICASSP2022 paper "Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music"

Official repository for the paper Singing Voice Graph Modeling for SingFake Detection (Interspeech 2024).

Transcribe music into lead sheets!

Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'

[SLT'24] The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model

Automatic Chord Recognition tools - ISMIR2021 Late-Breaking Demo presentation

Easily train a good VC model with voice data <= 10 mins!

only rmvpe

VOCANO: A note transcription framework for singing voice in polyphonic music

Repository for training models for music source separation.

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

Robust Singing Voice Transcription and MIDI Extraction

This repo provides the processed samples of the manuscript "MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-head Transformer with Convolution-augmented Jo…

multi-task and multi-track music transcription for everyone

This repo hosts the code and models of "Masked Autoencoders that Listen".

This is the material for paper "IMPROVING AUTOMATIC DRUM TRANSCRIPTION USING LARGE-SCALE AUDIO-TO-MIDI ALIGNED DATA"

MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]