{"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/audio-super-resolution-using-neural-networks","title":"Audio Super Resolution using Neural Networks","arxiv_id":"1708.00853","date":"2017-08-02","proceeding":null,"authors":["Volodymyr Kuleshov","S. Zayd Enam","Stefano Ermon"],"abstract":"We introduce a new audio processing technique that increases the sampling\nrate of signals such as speech or music using deep convolutional neural\nnetworks. Our model is trained on pairs of low and high-quality audio examples;\nat test-time, it predicts missing samples within a low-resolution signal in an\ninterpolation process similar to image super-resolution. Our method is simple\nand does not involve specialized audio processing techniques; in our\nexperiments, it outperforms baselines on standard speech and music benchmarks\nat upscaling ratios of 2x, 4x, and 6x. The method has practical applications in\ntelephony, compression, and text-to-speech generation; it demonstrates the\neffectiveness of feed-forward convolutional architectures on an audio\ngeneration task.","url_abs":"http://arxiv.org/abs/1708.00853v1","url_pdf":"http://arxiv.org/pdf/1708.00853v1.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":"audio-super-resolution-using-neural-networks","repo_url":"https://github.com/Amuzak-NTL/ASR-for-Speech-Recog","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"audio-super-resolution-using-neural-networks","repo_url":"https://github.com/TrizteX/Audio-SuperRes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"audio-super-resolution-using-neural-networks","repo_url":"https://github.com/johnathanchiu/audio-upsampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"audio-super-resolution-using-neural-networks","repo_url":"https://github.com/kuleshov/audio-super-res","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"audio-super-resolution","task_name":"Audio Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"1d-cnn","method_name":"1D CNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-super-resolution-on-piano-1","task":"Audio Super-Resolution","dataset":"Piano","model":"U-Net","rank_in_archive_order":3,"of":3,"metrics":{"Log-Spectral Distance":"3.4"},"uses_additional_data":false},{"leaderboard":"/sota/audio-super-resolution-on-vctk-multi-speaker-1","task":"Audio Super-Resolution","dataset":"VCTK Multi-Speaker","model":"U-Net","rank_in_archive_order":7,"of":7,"metrics":{"Log-Spectral Distance":"3.1"},"uses_additional_data":false},{"leaderboard":"/sota/audio-super-resolution-on-voice-bank-corpus-1","task":"Audio Super-Resolution","dataset":"Voice Bank corpus (VCTK)","model":"U-Net","rank_in_archive_order":3,"of":3,"metrics":{"Log-Spectral Distance":"3.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.00853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00853"}},"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/Amuzak-NTL/ASR-for-Speech-Recog","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kuleshov/audio-super-res","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/johnathanchiu/audio-upsampling","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TrizteX/Audio-SuperRes","reach":{"status":"unanswered"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"ba1df5452839f02f","entry":"butter_bandpass","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ba1df5452839f02f"}},{"code_sha256_prefix":"ab5d691d9fee133a","entry":"butter_bandpass_filter","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ab5d691d9fee133a"}},{"code_sha256_prefix":"368420e6b046e12a","entry":"trim_audio","repo":"johnathanchiu/audio-upsampling","repo_kind":"listed","path":"upsampling.py","file_url":"https://github.com/johnathanchiu/audio-upsampling/blob/HEAD/upsampling.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"368420e6b046e12a"}},{"code_sha256_prefix":"7bb46d84af38e43e","entry":"upsample","repo":"kuleshov/audio-super-res","repo_kind":"listed","path":"data/vctk/prep_vctk.py","file_url":"https://github.com/kuleshov/audio-super-res/blob/HEAD/data/vctk/prep_vctk.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7bb46d84af38e43e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}