Audio, Music, and AI Lab at SUTD

mustango

Mustango: Toward Controllable Text-to-Music Generation

Video2Music

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model

MidiCaps

A large-scale dataset of caption-annotated MIDI files.

MuVi

Predicting emotion from music videos: exploring the relative contribution of visual and auditory information on affective responses

Accented-TTS-MLVAE-ADV

PreBit

This is the repo accompanying the paper: "A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin"

awesome-MER

A curated list of Datasets, Models and Papers for Music Emotion Recognition (MER)

DisfluencySpeech

Resources for DisfluencySpeech

ai-audio-datasets-list

This is a list of datasets consisting of speech, music, and sound effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio applications. It is mainly used for speech recognition, speech synthesis, singing voice synthesis, music information retrieval, music generation, etc.

CVAE-Tacotron

Conditional VAE for Accented Speech Generation

genmusic_demo_list

a list of demo websites for automatic music generation research

singapore-music-classifier

Code for paper A dataset and classification model for Malay, Hindi, Tamil and Chinese music

DiffRoll

PyTorch implementation of DiffRoll, a diffusion-based generative automatic music transcription (AMT) model

nnAudio

Audio processing by using pytorch 1D convolution network

AMAAI-guidebook

AudioLoader

PyTorch Dataset for Speech and Music audio

CM-HRNN

Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure

Conditional-Drums-Generation-using-Compound-Word-Representations

Conditional Drums Generation using Compound Word Representations

datasets_emotion

This repository collects information about different data sets for Music Emotion Recognition.

demucs_lightning

Demucs Lightning: A PyTorch lightning version of Demucs with Hydra and Tensorboard features

emotionweb

Website emotion guidance

FundamentalMusicEmbedding

Fundamental Music Embedding, FME

HEAR_2021_NeurIPS_Challenge_SUTD_AMAAI

IJCNN2020_music_emotion

Regression-based Music Emotion Prediction using Triplet Neural Networks

Jointist

Official Implementation of Jointist

kylo-ren-app

Web interface for AI music generation models

LeadSheetGen_Valence

A novel seq2seq framework where high-level musicalities (such us the valence of the chord progression) are fed to the Encoder, and they are "translated" to lead sheet events in the Decoder. For further details please read and cite our paper:

MusIAC

music inpainting control

nnAudio-hear

ReconVAT

ReconVAT: a semi-supervised automatic music transcription (AMT) model