{"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/neural-audio-synthesis-of-musical-notes-with","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","arxiv_id":"1704.01279","date":"2017-04-05","proceeding":"ICML 2017 8","authors":["Jesse Engel","Cinjon Resnick","Adam Roberts","Sander Dieleman","Douglas Eck","Karen Simonyan","Mohammad Norouzi"],"abstract":"Generative models in vision have seen rapid progress due to algorithmic\nimprovements and the availability of high-quality image datasets. In this\npaper, we offer contributions in both these areas to enable similar progress in\naudio modeling. First, we detail a powerful new WaveNet-style autoencoder model\nthat conditions an autoregressive decoder on temporal codes learned from the\nraw audio waveform. Second, we introduce NSynth, a large-scale and high-quality\ndataset of musical notes that is an order of magnitude larger than comparable\npublic datasets. Using NSynth, we demonstrate improved qualitative and\nquantitative performance of the WaveNet autoencoder over a well-tuned spectral\nautoencoder baseline. Finally, we show that the model learns a manifold of\nembeddings that allows for morphing between instruments, meaningfully\ninterpolating in timbre to create new types of sounds that are realistic and\nexpressive.","url_abs":"http://arxiv.org/abs/1704.01279v1","url_pdf":"http://arxiv.org/pdf/1704.01279v1.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":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/JoshuaLeland/WaveNetEncoderContinuous","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/NoaCahan/WavenetAutoEncoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/Saran-nns/Edge-computing-with-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/facebookresearch/SING","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/morris-frank/nsynth-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/spear011/scm-dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/MindCode-4/code-8/tree/main/neural-audio-synthesis-wavenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"neural-audio-synthesis-of-musical-notes-with","repo_url":"https://github.com/MindSpore-scientific/code-6/tree/main/neural-audio-synthesis-wavenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"audio-synthesis","task_name":"Audio Synthesis"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[{"slug":"nsynth","name":"NSynth","full_name":"NSynth"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.01279","atlas_url":"https://app.syntology.ai/?focus=1704.01279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01279"}},"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/NoaCahan/WavenetAutoEncoder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-6/tree/main/neural-audio-synthesis-wavenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/morris-frank/nsynth-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/SING","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/spear011/scm-dataset","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-8/tree/main/neural-audio-synthesis-wavenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Saran-nns/Edge-computing-with-tf","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JoshuaLeland/WaveNetEncoderContinuous","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"ff5dbbd4100aabc8","entry":"decode_next","repo":"NoaCahan/WavenetAutoEncoder","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/NoaCahan/WavenetAutoEncoder/blob/HEAD/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff5dbbd4100aabc8"}},{"code_sha256_prefix":"9b138023564f070f","entry":"predict_next","repo":"NoaCahan/WavenetAutoEncoder","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/NoaCahan/WavenetAutoEncoder/blob/HEAD/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b138023564f070f"}},{"code_sha256_prefix":"68ea19d0fbeefdbd","entry":"sample_categorical","repo":"NoaCahan/WavenetAutoEncoder","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/NoaCahan/WavenetAutoEncoder/blob/HEAD/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"68ea19d0fbeefdbd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}