{"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/aero-audio-super-resolution-in-the-spectral","title":"AERO: Audio Super Resolution in the Spectral Domain","arxiv_id":"2211.12232","date":"2022-11-22","proceeding":null,"authors":["Moshe Mandel","Or Tal","Yossi Adi"],"abstract":"We present AERO, a audio super-resolution model that processes speech and music signals in the spectral domain. AERO is based on an encoder-decoder architecture with U-Net like skip connections. We optimize the model using both time and frequency domain loss functions. Specifically, we consider a set of reconstruction losses together with perceptual ones in the form of adversarial and feature discriminator loss functions. To better handle phase information the proposed method operates over the complex-valued spectrogram using two separate channels. Unlike prior work which mainly considers low and high frequency concatenation for audio super-resolution, the proposed method directly predicts the full frequency range. We demonstrate high performance across a wide range of sample rates considering both speech and music. AERO outperforms the evaluated baselines considering Log-Spectral Distance, ViSQOL, and the subjective MUSHRA test. Audio samples and code are available at https://pages.cs.huji.ac.il/adiyoss-lab/aero","url_abs":"https://arxiv.org/abs/2211.12232v2","url_pdf":"https://arxiv.org/pdf/2211.12232v2.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":"aero-audio-super-resolution-in-the-spectral","repo_url":"https://github.com/slp-rl/aero","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-super-resolution","task_name":"Audio Super-Resolution"},{"task_slug":"bandwidth-extension","task_name":"Bandwidth Extension"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/bandwidth-extension-on-vctk","task":"Bandwidth Extension","dataset":"VCTK","model":"AERO","rank_in_archive_order":1,"of":1,"metrics":{"LSD":"0.77"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.12232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12232"}},"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/slp-rl/aero","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"5f93dc40f3359937","entry":"average","repo":"slp-rl/aero","repo_kind":"official","path":"src/ddp/distrib.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/ddp/distrib.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":"5f93dc40f3359937"}},{"code_sha256_prefix":"c25a6ee5612eeb16","entry":"capture_init","repo":"slp-rl/aero","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/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":"c25a6ee5612eeb16"}},{"code_sha256_prefix":"53b356e89c900ed0","entry":"get_estimate","repo":"slp-rl/aero","repo_kind":"official","path":"src/enhance.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/enhance.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":"53b356e89c900ed0"}},{"code_sha256_prefix":"7b1e0fe56ce79b1a","entry":"get_lsd","repo":"slp-rl/aero","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/metrics.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":"7b1e0fe56ce79b1a"}},{"code_sha256_prefix":"096a41ecf25ab366","entry":"get_network_description","repo":"slp-rl/aero","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/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":"096a41ecf25ab366"}},{"code_sha256_prefix":"1831eb66490366a4","entry":"loader","repo":"slp-rl/aero","repo_kind":"official","path":"src/ddp/distrib.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/ddp/distrib.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":"1831eb66490366a4"}},{"code_sha256_prefix":"5a9f5aee3802a7b6","entry":"unfold","repo":"slp-rl/aero","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/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":"5a9f5aee3802a7b6"}},{"code_sha256_prefix":"16e325a4ba3f593b","entry":"wrap","repo":"slp-rl/aero","repo_kind":"official","path":"src/ddp/distrib.py","file_url":"https://github.com/slp-rl/aero/blob/HEAD/src/ddp/distrib.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":"16e325a4ba3f593b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}