paper-with-me

홈 › Papers

Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models

2024-06-12 · Javier Nistal, Marco Pasini, Cyran Aouameur, Maarten Grachten, Stefan Lattner

Recent advancements in deep generative models present new opportunities for music production but also pose challenges, such as high computational demands and limited audio quality. Moreover, current systems frequently rely solely on text input and typically focus on producing complete musical pieces, which is incompatible with existing workflows in music production. To address these issues, we introduce "Diff-A-Riff," a Latent Diffusion Model designed to generate high-quality instrumental accompaniments adaptable to any musical context. This model offers control through either audio references, text prompts, or both, and produces 48kHz pseudo-stereo audio while significantly reducing inference time and memory usage. We demonstrate the model's capabilities through objective metrics and subjective listening tests, with extensive examples available on the accompanying website: sonycslparis.github.io/diffariff-companion/

📄 PDF Abstract BibTeX arXiv:2406.08384

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Similar Papers 제목 키워드 기반

SAMUeL: Efficient Vocal-Conditioned Music Generation via Soft Alignment Attention and Latent Diffusion

2025-07-26 · Hei Shing Cheung, Boya Zhang, Jonathan H. Chan arxiv

We present a lightweight latent diffusion model for vocal-conditioned musical accompaniment generation that addresses critical limitations in existing music AI systems. Our approach introduces a novel soft alignment atte…

Music Generation

DARC: Drum accompaniment generation with fine-grained rhythm control

2026-01-05 · Trey Brosnan arxiv

In music creation, rapid prototyping is essential for exploring and refining ideas, yet existing generative tools often fall short when users require both structural control and stylistic flexibility. Prior approaches in…

parameter-efficient fine-tuning

Towards Real-Time Human-AI Musical Co-Performance: Accompaniment Generation with Latent Diffusion Models and MAX/MSP

2026-04-08 · Tornike Karchkhadze, Shlomo Dubnov arxiv

We present a framework for real-time human-AI musical co-performance, in which a latent diffusion model generates instrumental accompaniment in response to a live stream of context audio. The system combines a MAX/MSP fr…

DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

2025-03-03 · Ziqian Ning, Huakang Chen, Yuepeng Jiang, Chunbo Hao 외

Recent advancements in music generation have garnered significant attention, yet existing approaches face critical limitations. Some current generative models can only synthesize either the vocal track or the accompanime…

Music Generation

D3PIA: A Discrete Denoising Diffusion Model for Piano Accompaniment Generation From Lead sheet

2026-02-03 · Eunjin Choi, Hounsu Kim, Hayeon Bang, Taegyun Kwon 외 arxiv

Generating piano accompaniments in the symbolic music domain is a challenging task that requires producing a complete piece of piano music from given melody and chord constraints, such as those provided by a lead sheet. …