Everybody Compose: Deep Beats To Music

2023-06-09 · Conghao Shen, Violet Z. Yao, Yixin Liu

This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods - LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation - are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or ``recoloring'' beat sequences from existing works.

📄 PDF Abstract BibTeX arXiv:2306.06284

Code (1)

tsunrise/everybody-compose 공식 구현 pytorch

Tasks

Position

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Position-Wise Feed-Forward Layer 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Multi-Head Attention 설명 없음

Synchronising speech segments with musical beats in Mandarin and English singing

2021-06-18 · Cong Zhang, Jian Zhu

Generating synthesised singing voice with models trained on speech data has many advantages due to the models' flexibility and controllability. However, since the information about the temporal relationship between segme…

Let Your Video Listen to Your Music!

2025-06-23 · Xinyu Zhang, Dong Gong, Zicheng Duan, Anton Van Den Hengel 외

Aligning the rhythm of visual motion in a video with a given music track is a practical need in multimedia production, yet remains an underexplored task in autonomous video editing. Effective alignment between motion and…

GPU Music Generation Rhythm Video Editing+1

Relationships between Keywords and Strong Beats in Lyrical Music

2024-12-05 · Callie C. Liao, Duoduo Liao, Ellie L. Zhang

Artificial Intelligence (AI) song generation has emerged as a popular topic, yet the focus on exploring the latent correlations between specific lyrical and rhythmic features remains limited. In contrast, this pilot stud…

Rhythm

Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models

2024-08-05 · Pushkar Jajoria, James McDermott

This study introduces a text-conditioned approach to generating drumbeats with Latent Diffusion Models (LDMs). It uses informative conditioning text extracted from training data filenames. By pretraining a text and drumb…

Contrastive Learning

BACHI: Boundary-Aware Symbolic Chord Recognition Through Masked Iterative Decoding on Pop and Classical Music

2025-10-08 · Mingyang Yao, Ke Chen, Shlomo Dubnov, Taylor Berg-Kirkpatrick arxiv

Automatic chord recognition (ACR) via deep learning models has gradually achieved promising recognition accuracy, yet two key challenges remain. First, prior work has primarily focused on audio-domain ACR, while symbolic…

Boundary Detection