{"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/melnet-a-generative-model-for-audio-in-the","title":"MelNet: A Generative Model for Audio in the Frequency Domain","arxiv_id":"1906.01083","date":"2019-06-04","proceeding":null,"authors":["Sean Vasquez","Mike Lewis"],"abstract":"Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can be more tractably modelled in two-dimensional time-frequency representations such as spectrograms. By leveraging this representational advantage, in conjunction with a highly expressive probabilistic model and a multiscale generation procedure, we design a model capable of generating high-fidelity audio samples which capture structure at timescales that time-domain models have yet to achieve. We apply our model to a variety of audio generation tasks, including unconditional speech generation, music generation, and text-to-speech synthesis---showing improvements over previous approaches in both density estimates and human judgments.","url_abs":"https://arxiv.org/abs/1906.01083v1","url_pdf":"https://arxiv.org/pdf/1906.01083v1.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":"melnet-a-generative-model-for-audio-in-the","repo_url":"https://github.com/Talk2Levi/DJL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"melnet-a-generative-model-for-audio-in-the","repo_url":"https://github.com/YuvalBecker/MelNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"melnet-a-generative-model-for-audio-in-the","repo_url":"https://github.com/YuvalBecker/MelNet-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"melnet-a-generative-model-for-audio-in-the","repo_url":"https://github.com/jacksonkaunismaa/neural-music","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"melnet-a-generative-model-for-audio-in-the","repo_url":"https://github.com/fatchord/MelNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"music-generation","task_name":"Music Generation"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.01083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01083"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/Talk2Levi/DJL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fatchord/MelNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YuvalBecker/MelNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YuvalBecker/MelNet-Tensorflow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jacksonkaunismaa/neural-music","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_fixture":3},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"ba1df5452839f02f","entry":"butter_bandpass","repo":"YuvalBecker/MelNet","repo_kind":"listed","path":"making_mel_Spec.py","file_url":"https://github.com/YuvalBecker/MelNet/blob/HEAD/making_mel_Spec.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba1df5452839f02f"}},{"code_sha256_prefix":"ab5d691d9fee133a","entry":"butter_bandpass_filter","repo":"YuvalBecker/MelNet","repo_kind":"listed","path":"making_mel_Spec.py","file_url":"https://github.com/YuvalBecker/MelNet/blob/HEAD/making_mel_Spec.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab5d691d9fee133a"}},{"code_sha256_prefix":"87477478d9b7de10","entry":"generating_from_disribution_new","repo":"YuvalBecker/MelNet","repo_kind":"listed","path":"MelNet.py","file_url":"https://github.com/YuvalBecker/MelNet/blob/HEAD/MelNet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87477478d9b7de10"}},{"code_sha256_prefix":"3adafbc146d4da00","entry":"overlap","repo":"YuvalBecker/MelNet","repo_kind":"listed","path":"making_mel_Spec.py","file_url":"https://github.com/YuvalBecker/MelNet/blob/HEAD/making_mel_Spec.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3adafbc146d4da00"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}