ta603

VoiceFlow-TTS

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

RefinPaint

CHAD

Official Code of "A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-by-Humming Task" (ISMIR 2023)

PyMusicLooper

A python program for repeating music endlessly and creating seamless music loops, with play/export/tagging support.

geomloss

Geometric loss functions between point clouds, images and volumes

edm2

Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

symusic

A swift and unified toolkit for symbolic music processing

versatile_audio_super_resolution

Versatile audio super resolution (any -> 48kHz) with AudioSR.

Muskits

An opensource music processing toolkit

singing_transcription_ICASSP2021

The source code and pre-trained model of the paper "On the Preparation and Validation of a Large-scale Dataset"

phoneme-informed-note-level-singing-transcription

A pretrained model for "A Phoneme-informed Neural Network Model for Note-level Singing Transcription", ICASSP 2023

icassp2022-vocal-transcription

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

CSD_reannotation

Re-annotation for CSD dataset for singing transcription

Dance2Music

Automatic Dance-driven Music Generation

video-bgm-generation

Video Background Music Generation with Controllable Music Transformer (ACM MM 2021 Best Paper Award)

CDCD

[ICLR2023] Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation (CDCD).

D2M-GAN

[ECCV2022] D2M-GAN for music generation from dance videos

ismir2017-deepsalience

Companion code for ISMIR 2017 paper "Deep Salience Representations for $F_0$ Estimation in Polyphonic Music"

Melody-extraction-with-melodic-segnet

The source code of "A Streamlined Encoder/Decoder Architecture for Melody Extraction"

hFT-Transformer

Pytorch implementation of automatic music transcription method that uses a two-level hierarchical frequency-time Transformer architecture (hFT-Transformer).

Bailando

Code for CVPR 2022 paper "Bailando: 3D dance generation via Actor-Critic GPT with Choreographic Memory"

EDGE

Official PyTorch Implementation of EDGE (CVPR 2023)

CQTdiff

Official repository of the paper "Solving Audio Inverse Problems with a Diffusion Model", submitted to ICASSP 23

jamendolyrics

Jamendo music dataset with time-aligned lyrics for lyrics alignment evaluation

lyrics-melody

Lyrics and Vocal Melody Generation conditioned on Accompaniment

anticipation

Anticipatory Autoregressive Models

Self-supervised_Metric_Learning

genmusic_demo_list

a list of demo websites for automatic music generation research

open-musiclm

Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.

charsiu

Charsiu: A neural phonetic aligner.