paper-with-me

홈 › Papers

Song From PI: A Musically Plausible Network for Pop Music Generation

2016-11-10 · Hang Chu, Raquel Urtasun, Sanja Fidler

We present a novel framework for generating pop music. Our model is a hierarchical Recurrent Neural Network, where the layers and the structure of the hierarchy encode our prior knowledge about how pop music is composed. In particular, the bottom layers generate the melody, while the higher levels produce the drums and chords. We conduct several human studies that show strong preference of our generated music over that produced by the recent method by Google. We additionally show two applications of our framework: neural dancing and karaoke, as well as neural story singing.

📄 PDF Abstract BibTeX arXiv:1611.03477

Code (0)

등록된 구현이 없습니다.

Tasks

Music Generation

Similar Papers 제목 키워드 기반

High-Level Control of Drum Track Generation Using Learned Patterns of Rhythmic Interaction

2019-08-02 · Stefan Lattner, Maarten Grachten

Spurred by the potential of deep learning, computational music generation has gained renewed academic interest. A crucial issue in music generation is that of user control, especially in scenarios where the music generat…

Music Generation

SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment

2026-04-16 · Dapeng Wu, Shun Lei, Wei Tan, Guangzheng Li 외 arxiv

Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In th…

Learning Transposition-Invariant Interval Features from Symbolic Music and Audio

2018-06-21 · Stefan Lattner, Maarten Grachten, Gerhard Widmer

Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in musi…

musicnn: Pre-trained convolutional neural networks for music audio tagging

2019-09-14 · Jordi Pons, Xavier Serra

Pronounced as "musician", the musicnn library contains a set of pre-trained musically motivated convolutional neural networks for music audio tagging: https://github.com/jordipons/musicnn. This repository also includes s…

Audio TaggingTransfer Learning

An empirical approach to the relationship between emotion and music production quality

2018-03-29

In music production, the role of the mix engineer is to take recorded music and convey the expressed emotions as professionally sounding as possible. We investigated the relationship between music production quality and …