# JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment

arXiv: https://arxiv.org/abs/2507.20880 · HTML: https://mlsanity.com/paper/2507.20880/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model](https://mlsanity.com/paper/2304.13731/) (2023)
- [Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization](https://mlsanity.com/paper/2404.09956/) (2024)
- [MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies](https://mlsanity.com/paper/2308.01546/) (2023)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization](https://mlsanity.com/paper/2412.21037/) (2024)
- [ACE-Step: A Step Towards Music Generation Foundation Model](https://mlsanity.com/paper/2506.00045/) (2025)
- [DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion](https://mlsanity.com/paper/2503.01183/) (2025)
- [MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2502.18924/) (2025)
- [SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation](https://mlsanity.com/paper/2502.13128/) (2025)
- [All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio](https://mlsanity.com/paper/2307.16425/) (2023)
- [LeVo: High-Quality Song Generation with Multi-Preference Alignment](https://mlsanity.com/paper/2506.07520/) (2025)
- [SongCreator: Lyrics-based Universal Song Generation](https://mlsanity.com/paper/2409.06029/) (2024)
- [DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization](https://mlsanity.com/paper/2507.12890/) (2025)

## Built on by (most cited first, 9 of 9)

- [Stable Audio 3](https://mlsanity.com/paper/2605.17991/) (2026)
- [CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction](https://mlsanity.com/paper/2603.00610/) (2026)
- [MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI](https://mlsanity.com/paper/2608.30940/) (2026)
- [LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation](https://mlsanity.com/paper/2604.11052/) (2026)
- [Auditing Training Data in Generative Music Models via Black-Box Membership Inference](https://mlsanity.com/paper/2605.29202/) (2026)
- [SegTune: Structured and Fine-Grained Control for Song Generation](https://mlsanity.com/paper/2606.02638/) (2026)
- [MusicMark: A Robust Generative Watermarking Framework for Music Generation](https://mlsanity.com/paper/2607.11117/) (2026)
- [MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation](https://mlsanity.com/paper/2607.26698/) (2026)
- [TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models](https://mlsanity.com/paper/2610.00835/) (2026)

## Abstract (arXiv)

Diffusion and flow-matching models have revolutionized automatic text-to-audio generation in recent times. These models are increasingly capable of generating high quality and faithful audio outputs capturing to speech and acoustic events. However, there is still much room for improvement in creative audio generation that primarily involves music and songs. Recent open lyrics-to-song models, such as, DiffRhythm, ACE-Step, and LeVo, have set an acceptable standard in automatic song generation for recreational use. However, these models lack fine-grained word-level controllability often desired by musicians in their workflows. To the best of our knowledge, our flow-matching-based JAM is the first effort toward endowing word-level timing and duration control in song generation, allowing fine-grained vocal control. To enhance the quality of generated songs to better align with human preferences, we implement aesthetic alignment through Direct Preference Optimization, which iteratively refines the model using a synthetic dataset, eliminating the need or manual data annotations. Furthermore, we aim to standardize the evaluation of such lyrics-to-song models through our public evaluation dataset JAME. We show that JAM outperforms the existing models in terms of the music-specific attributes.