# Multi-instrument Music Synthesis with Spectrogram Diffusion

arXiv: https://arxiv.org/abs/2206.05408 · HTML: https://mlsanity.com/paper/2206.05408/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 64 of its 76 references that are in the map.
- First posted on arXiv 11 Jun 2022.

## Placed in

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

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [Scaling Up Models and Data with textttt5x and textttseqio](https://mlsanity.com/paper/2203.17189/) (2022)

## Built on by (most cited first, 30 of 42)

- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [DITTO: Diffusion Inference-Time T-Optimization for Music Generation](https://mlsanity.com/paper/2401.12179/) (2024)
- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [Solving Audio Inverse Problems with a Diffusion Model](https://mlsanity.com/paper/2210.15228/) (2022)
- [SingSong: Generating musical accompaniments from singing](https://mlsanity.com/paper/2301.12662/) (2023)
- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [StemGen: A music generation model that listens](https://mlsanity.com/paper/2312.08723/) (2023)
- [Exploring Diffusion Models for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2304.05841/) (2023)
- [Attributing Image Generative Models using Latent Fingerprints](https://mlsanity.com/paper/2304.09752/) (2023)
- [Long-Term Rhythmic Video Soundtracker](https://mlsanity.com/paper/2305.01319/) (2023)
- [Discrete Diffusion Probabilistic Models for Symbolic Music Generation](https://mlsanity.com/paper/2305.09489/) (2023)
- [EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis](https://mlsanity.com/paper/2311.08667/) (2023)
- [DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability](https://mlsanity.com/paper/2210.05148/) (2022)
- [LongDanceDiff: Long-term Dance Generation with Conditional Diffusion Model](https://mlsanity.com/paper/2308.11945/) (2023)
- [DExter: Learning and Controlling Performance Expression with Diffusion Models](https://mlsanity.com/paper/2406.14850/) (2024)
- [Combining audio control and style transfer using latent diffusion](https://mlsanity.com/paper/2408.00196/) (2024)
- [Timbre transfer using image-to-image denoising diffusion implicit models](https://mlsanity.com/paper/2307.04586/) (2023)
- [Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio](https://mlsanity.com/paper/2505.12863/) (2025)
- [AudioSlots: A slot-centric generative model for audio separation](https://mlsanity.com/paper/2305.05591/) (2023)
- [Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis](https://mlsanity.com/paper/2309.12283/) (2023)
- [Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting](https://mlsanity.com/paper/2401.13498/) (2024)
- [A Survey of Deep Learning Audio Generation Methods](https://mlsanity.com/paper/2406.00146/) (2024)
- [Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss](https://mlsanity.com/paper/2403.16728/) (2024)
- [A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives](https://mlsanity.com/paper/2504.00837/) (2025)
- [WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation](https://mlsanity.com/paper/2510.11839/) (2025)
- [MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage](https://mlsanity.com/paper/2403.10024/) (2024)
- [Why Perturbing Symbolic Music is Necessary: Fitting the Distribution of Never-used Notes through a Joint Probabilistic Diffusion Model](https://mlsanity.com/paper/2408.01950/) (2024)
- [Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training](https://mlsanity.com/paper/2512.02652/) (2025)
- [Distribution Preserving Source Separation With Time Frequency Predictive Models](https://mlsanity.com/paper/2303.05896/) (2023)

## Abstract (arXiv)

An ideal music synthesizer should be both interactive and expressive, generating high-fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural synthesizers have exhibited a tradeoff between domain-specific models that offer detailed control of only specific instruments, or raw waveform models that can train on any music but with minimal control and slow generation. In this work, we focus on a middle ground of neural synthesizers that can generate audio from MIDI sequences with arbitrary combinations of instruments in realtime. This enables training on a wide range of transcription datasets with a single model, which in turn offers note-level control of composition and instrumentation across a wide range of instruments. We use a simple two-stage process: MIDI to spectrograms with an encoder-decoder Transformer, then spectrograms to audio with a generative adversarial network (GAN) spectrogram inverter. We compare training the decoder as an autoregressive model and as a Denoising Diffusion Probabilistic Model (DDPM) and find that the DDPM approach is superior both qualitatively and as measured by audio reconstruction and Fr'echet distance metrics. Given the interactivity and generality of this approach, we find this to be a promising first step towards interactive and expressive neural synthesis for arbitrary combinations of instruments and notes.