paper-with-me

홈 › Papers

MusicGen-Chord: Advancing Music Generation through Chord Progressions and Interactive Web-UI

2024-11-30 · Jongmin Jung, Andreas Jansson, Dasaem Jeong

MusicGen is a music generation language model (LM) that can be conditioned on textual descriptions and melodic features. We introduce MusicGen-Chord, which extends this capability by incorporating chord progression features. This model modifies one-hot encoded melody chroma vectors into multi-hot encoded chord chroma vectors, enabling the generation of music that reflects both chord progressions and textual descriptions. Furthermore, we developed MusicGen-Remixer, an application utilizing MusicGen-Chord to generate remixes of input music conditioned on textual descriptions. Both models are integrated into Replicate's web-UI using cog, facilitating broad accessibility and user-friendly controllable interaction for creating and experiencing AI-generated music.

📄 PDF Abstract BibTeX arXiv:2412.00325

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMusic Generation

Similar Papers 제목 키워드 기반

Do Music Generation Models Encode Music Theory?

2024-10-01 · Megan Wei, Michael Freeman, Chris Donahue, Chen Sun

Music foundation models possess impressive music generation capabilities. When people compose music, they may infuse their understanding of music into their work, by using notes and intervals to craft melodies, chords to…

Emotion RecognitionGenre classificationInformation RetrievalMusic Generation+1

MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation

2024-07-21 · Yun-Han Lan, Wen-Yi Hsiao, Hao-Chung Cheng, Yi-Hsuan Yang

Existing text-to-music models can produce high-quality audio with great diversity. However, textual prompts alone cannot precisely control temporal musical features such as chords and rhythm of the generated music. To ad…

DiversityMusic GenerationRhythmText-to-Music Generation

Simple and Controllable Music Generation

2023-06-08 · NeurIPS 2023 11 · Jade Copet, Felix Kreuk, Itai Gat, Tal Remez 외

We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, Mus…

Language ModelingLanguage ModellingMusic GenerationText-to-Music Generation

Mustango: Toward Controllable Text-to-Music Generation

2023-11-14 · Jan Melechovsky, Zixun Guo, Deepanway Ghosal, Navonil Majumder 외

The quality of the text-to-music models has reached new heights due to recent advancements in diffusion models. The controllability of various musical aspects, however, has barely been explored. In this paper, we propose…

Data AugmentationDenoisingInformation RetrievalMusic Generation+2

Steering Autoregressive Music Generation with Recursive Feature Machines

2025-10-21 · Daniel Zhao, Daniel Beaglehole, Taylor Berg-Kirkpatrick, Julian McAuley 외 arxiv

Controllable music generation remains a significant challenge, with existing methods often requiring model retraining or introducing audible artifacts. We introduce MusicRFM, a framework that adapts Recursive Feature Mac…

Music Generation