# LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation

arXiv: https://arxiv.org/abs/2604.11052 · HTML: https://mlsanity.com/paper/2604.11052/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 32 of its 51 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 32)

- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://mlsanity.com/paper/2505.19223/) (2025)
- [Adapting Frechet Audio Distance for Generative Music Evaluation](https://mlsanity.com/paper/2311.01616/) (2023)
- [YuE: Scaling Open Foundation Models for Long-Form Music Generation](https://mlsanity.com/paper/2503.08638/) (2025)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [VampNet: Music Generation via Masked Acoustic Token Modeling](https://mlsanity.com/paper/2307.04686/) (2023)
- [ACE-Step: A Step Towards Music Generation Foundation Model](https://mlsanity.com/paper/2506.00045/) (2025)
- [SingSong: Generating musical accompaniments from singing](https://mlsanity.com/paper/2301.12662/) (2023)
- [SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation](https://mlsanity.com/paper/2502.13128/) (2025)
- [SongEval: A Benchmark Dataset for Song Aesthetics Evaluation](https://mlsanity.com/paper/2505.10793/) (2025)
- [SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement](https://mlsanity.com/paper/2506.07634/) (2025)
- [AccoMontage: Accompaniment Arrangement via Phrase Selection and Style Transfer](https://mlsanity.com/paper/2108.11213/) (2021)
- [Seed-Music: A Unified Framework for High Quality and Controlled Music Generation](https://mlsanity.com/paper/2409.09214/) (2024)
- [Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking](https://mlsanity.com/paper/2505.18495/) (2025)
- [Anchored Diffusion Language Model](https://mlsanity.com/paper/2505.18456/) (2025)
- [SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision](https://mlsanity.com/paper/2510.02797/) (2025)
- [DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matching](https://mlsanity.com/paper/2510.22950/) (2025)
- [Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer](https://mlsanity.com/paper/2410.05151/) (2024)
- [MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners](https://mlsanity.com/paper/2506.18729/) (2025)
- [JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment](https://mlsanity.com/paper/2507.20880/) (2025)
- [Discrete Diffusion Language Model for Efficient Text Summarization](https://mlsanity.com/paper/2407.10998/) (2024)
- [DIFFA: Large Language Diffusion Models Can Listen and Understand](https://mlsanity.com/paper/2507.18452/) (2025)
- [Pre-trained Token-replaced Detection Model as Few-shot Learner](https://mlsanity.com/paper/2203.03235/) (2022)
- [SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor](https://mlsanity.com/paper/2412.13786/) (2024)
- [STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning](https://mlsanity.com/paper/2504.05690/) (2025)
- [FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation](https://mlsanity.com/paper/2405.07682/) (2024)
- [A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives](https://mlsanity.com/paper/2504.00837/) (2025)
- [Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization](https://mlsanity.com/paper/2408.15176/) (2024)
- [SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation](https://mlsanity.com/paper/2602.19976/) (2026)
- [Emotion-Guided Music Accompaniment Generation Based on Variational Autoencoder](https://mlsanity.com/paper/2307.04015/) (2023)

## Abstract (arXiv)

Vocal-to-accompaniment (V2A) generation, which aims to transform a raw vocal recording into a fully arranged accompaniment, inherently requires jointly addressing an accompaniment trilemma: preserving acoustic authenticity, maintaining global coherence with the vocal track, and producing dynamic orchestration across a full song. Existing open-source approaches typically make compromises among these goals. Continuous-latent generation models can capture long musical spans but often struggle to preserve fine-grained acoustic detail. In contrast, discrete autoregressive models retain local fidelity but suffer from unidirectional generation and error accumulation in extended contexts. We present LaDA-Band, an end-to-end framework that introduces Discrete Masked Diffusion to the V2A task. Our approach formulates V2A generation as Discrete Masked Diffusion, i.e., a global, non-autoregressive denoising formulation that combines the representational advantages of discrete audio codec tokens with full-sequence bidirectional context modeling. This design improves long-range structural consistency and temporal synchronization while preserving crisp acoustic details. Built on this formulation, LaDA-Band further introduces a dual-track prefix-conditioning architecture, an auxiliary replaced-token detection objective for weakly anchored accompaniment regions, and a two-stage progressive curriculum to scale Discrete Masked Diffusion to full-song vocal-to-accompaniment generation. Extensive experiments on both academic and real-world benchmarks show that LaDA-Band consistently improves acoustic authenticity, global coherence, and dynamic orchestration over existing baselines, while maintaining strong performance even without auxiliary reference audio. Codes and audio samples are available at https://github.com/Duoluoluos/TME-LaDA-Band .