{"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/samplernn-an-unconditional-end-to-end-neural","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","arxiv_id":"1612.07837","date":"2016-12-22","proceeding":null,"authors":["Soroush Mehri","Kundan Kumar","Ishaan Gulrajani","Rithesh Kumar","Shubham Jain","Jose Sotelo","Aaron Courville","Yoshua Bengio"],"abstract":"In this paper we propose a novel model for unconditional audio generation\nbased on generating one audio sample at a time. We show that our model, which\nprofits from combining memory-less modules, namely autoregressive multilayer\nperceptrons, and stateful recurrent neural networks in a hierarchical structure\nis able to capture underlying sources of variations in the temporal sequences\nover very long time spans, on three datasets of different nature. Human\nevaluation on the generated samples indicate that our model is preferred over\ncompeting models. We also show how each component of the model contributes to\nthe exhibited performance.","url_abs":"http://arxiv.org/abs/1612.07837v2","url_pdf":"http://arxiv.org/pdf/1612.07837v2.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":"samplernn-an-unconditional-end-to-end-neural","repo_url":"https://github.com/soroushmehr/sampleRNN_ICLR2017","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"samplernn-an-unconditional-end-to-end-neural","repo_url":"https://github.com/cchinchristopherj/Concert-of-Whales","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"samplernn-an-unconditional-end-to-end-neural","repo_url":"https://github.com/deepsound-project/samplernn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"samplernn-an-unconditional-end-to-end-neural","repo_url":"https://github.com/dada-bots/dadabots_sampleRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-synthesis-on-blizzard-challenge-2013","task":"Speech Synthesis","dataset":"Blizzard Challenge 2013","model":"SampleRNN (3-tier)","rank_in_archive_order":1,"of":2,"metrics":{"NLL":"1.387"},"uses_additional_data":false},{"leaderboard":"/sota/speech-synthesis-on-blizzard-challenge-2013","task":"Speech Synthesis","dataset":"Blizzard Challenge 2013","model":"SampleRNN (2-tier)","rank_in_archive_order":2,"of":2,"metrics":{"NLL":"1.392"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.07837","atlas_url":"https://app.syntology.ai/?focus=1612.07837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.07837"}},"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/cchinchristopherj/Concert-of-Whales","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepsound-project/samplernn-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soroushmehr/sampleRNN_ICLR2017","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dada-bots/dadabots_sampleRNN","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":8,"ran":0,"repositories":2}},"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":"b66f9b2d11a10ef2","entry":"find_dataset","repo":"soroushmehr/sampleRNN_ICLR2017","repo_kind":"official","path":"datasets/dataset.py","file_url":"https://github.com/soroushmehr/sampleRNN_ICLR2017/blob/HEAD/datasets/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b66f9b2d11a10ef2"}},{"code_sha256_prefix":"483324e37147887a","entry":"find_dataset","repo":"dada-bots/dadabots_sampleRNN","repo_kind":"listed","path":"datasets/dataset.py","file_url":"https://github.com/dada-bots/dadabots_sampleRNN/blob/HEAD/datasets/dataset.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":"483324e37147887a"}},{"code_sha256_prefix":"76a3848fdc07a751","entry":"gradient_clipping","repo":"deepsound-project/samplernn-pytorch","repo_kind":"listed","path":"optim.py","file_url":"https://github.com/deepsound-project/samplernn-pytorch/blob/HEAD/optim.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76a3848fdc07a751"}},{"code_sha256_prefix":"bf123cbc1a5c7c22","entry":"linear2mu","repo":"soroushmehr/sampleRNN_ICLR2017","repo_kind":"official","path":"datasets/dataset.py","file_url":"https://github.com/soroushmehr/sampleRNN_ICLR2017/blob/HEAD/datasets/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf123cbc1a5c7c22"}},{"code_sha256_prefix":"bcb1aa73abd49bb2","entry":"linear2mu","repo":"dada-bots/dadabots_sampleRNN","repo_kind":"listed","path":"datasets/dataset.py","file_url":"https://github.com/dada-bots/dadabots_sampleRNN/blob/HEAD/datasets/dataset.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":"bcb1aa73abd49bb2"}},{"code_sha256_prefix":"10c1a66056242af7","entry":"linear_dequantize","repo":"deepsound-project/samplernn-pytorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/deepsound-project/samplernn-pytorch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10c1a66056242af7"}},{"code_sha256_prefix":"1d698a1b8ebdffef","entry":"linear_quantize","repo":"deepsound-project/samplernn-pytorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/deepsound-project/samplernn-pytorch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d698a1b8ebdffef"}},{"code_sha256_prefix":"bfa157a2f01ee323","entry":"mu2linear","repo":"soroushmehr/sampleRNN_ICLR2017","repo_kind":"official","path":"datasets/dataset.py","file_url":"https://github.com/soroushmehr/sampleRNN_ICLR2017/blob/HEAD/datasets/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfa157a2f01ee323"}},{"code_sha256_prefix":"08d55cf94660e24e","entry":"mu2linear","repo":"dada-bots/dadabots_sampleRNN","repo_kind":"listed","path":"datasets/dataset.py","file_url":"https://github.com/dada-bots/dadabots_sampleRNN/blob/HEAD/datasets/dataset.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":"08d55cf94660e24e"}},{"code_sha256_prefix":"75e69c94dae9a379","entry":"q_zero","repo":"deepsound-project/samplernn-pytorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/deepsound-project/samplernn-pytorch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75e69c94dae9a379"}},{"code_sha256_prefix":"c05eb4083a6e42d3","entry":"sequence_nll_loss_bits","repo":"deepsound-project/samplernn-pytorch","repo_kind":"listed","path":"nn.py","file_url":"https://github.com/deepsound-project/samplernn-pytorch/blob/HEAD/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c05eb4083a6e42d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}