{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-instrument-music-synthesis-with","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","arxiv_id":"2206.05408","date":"2022-06-11","proceeding":null,"authors":["Curtis Hawthorne","Ian Simon","Adam Roberts","Neil Zeghidour","Josh Gardner","Ethan Manilow","Jesse Engel"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2206.05408v3","url_pdf":"https://arxiv.org/pdf/2206.05408v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-instrument-music-synthesis-with","repo_url":"https://github.com/magenta/music-spectrogram-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"music-generation","task_name":"Music Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.05408","atlas_url":"https://app.syntology.ai/?focus=2206.05408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05408"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/magenta/music-spectrogram-diffusion","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a6a561cef1b6be1f","entry":"add_unique_id","repo":"magenta/music-spectrogram-diffusion","repo_kind":"official","path":"music_spectrogram_diffusion/preprocessors.py","file_url":"https://github.com/magenta/music-spectrogram-diffusion/blob/HEAD/music_spectrogram_diffusion/preprocessors.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6a561cef1b6be1f"}},{"code_sha256_prefix":"84507ed9f1c14e49","entry":"sinusoidal","repo":"magenta/music-spectrogram-diffusion","repo_kind":"official","path":"music_spectrogram_diffusion/layers.py","file_url":"https://github.com/magenta/music-spectrogram-diffusion/blob/HEAD/music_spectrogram_diffusion/layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"84507ed9f1c14e49"}},{"code_sha256_prefix":"dac0288079ac279f","entry":"dot_product_attention","repo":"magenta/music-spectrogram-diffusion","repo_kind":"official","path":"music_spectrogram_diffusion/layers.py","file_url":"https://github.com/magenta/music-spectrogram-diffusion/blob/HEAD/music_spectrogram_diffusion/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dac0288079ac279f"}},{"code_sha256_prefix":"1184cae8ca10c644","entry":"make_attention_mask","repo":"magenta/music-spectrogram-diffusion","repo_kind":"official","path":"music_spectrogram_diffusion/layers.py","file_url":"https://github.com/magenta/music-spectrogram-diffusion/blob/HEAD/music_spectrogram_diffusion/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1184cae8ca10c644"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}