{"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/whisper-at-noise-robust-automatic-speech","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","arxiv_id":"2307.03183","date":"2023-07-06","proceeding":null,"authors":["Yuan Gong","Sameer Khurana","Leonid Karlinsky","James Glass"],"abstract":"In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whisper, and training a lightweight audio tagging model on top of it. With <1% extra computational cost, Whisper-AT can recognize audio events, in addition to spoken text, in a single forward pass.","url_abs":"https://arxiv.org/abs/2307.03183v1","url_pdf":"https://arxiv.org/pdf/2307.03183v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"whisper-at-noise-robust-automatic-speech","repo_url":"https://github.com/YuanGongND/whisper-at","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.03183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03183"}},"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/YuanGongND/whisper-at","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran":14,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":17,"ran":15,"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":"d358725a8a4995c9","entry":"calculate_stats","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/stats.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/stats.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d358725a8a4995c9"}},{"code_sha256_prefix":"5ee11f4af0d2fc1e","entry":"computeMatchmap","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/util.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5ee11f4af0d2fc1e"}},{"code_sha256_prefix":"e469cef4384ff73a","entry":"d_prime","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/stats.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/stats.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e469cef4384ff73a"}},{"code_sha256_prefix":"638f8f1d05f173c7","entry":"fileList","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/noise_robust_asr/asr_experiments/transcribe_whisper.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/noise_robust_asr/asr_experiments/transcribe_whisper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"638f8f1d05f173c7"}},{"code_sha256_prefix":"e3a904304feac15a","entry":"get_feat_shape","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/compute_flops.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/compute_flops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e3a904304feac15a"}},{"code_sha256_prefix":"64ddb5ad0af650e6","entry":"get_immediate_files","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/noise_robust_asr/asr_experiments/transcribe_whisper.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/noise_robust_asr/asr_experiments/transcribe_whisper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"64ddb5ad0af650e6"}},{"code_sha256_prefix":"2bb7da1cdb95b512","entry":"get_immediate_files_with_extension","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/rename_state_dict.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/rename_state_dict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2bb7da1cdb95b512"}},{"code_sha256_prefix":"c15efdd12442aeb4","entry":"lookup_list","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/dataloader_feat.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/dataloader_feat.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c15efdd12442aeb4"}},{"code_sha256_prefix":"a8fb3f62e2a901d7","entry":"make_index_dict","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/dataloader_feat.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/dataloader_feat.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a8fb3f62e2a901d7"}},{"code_sha256_prefix":"ad2738e74fab6072","entry":"make_index_dict","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/gen_weight_file.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/gen_weight_file.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ad2738e74fab6072"}},{"code_sha256_prefix":"cbf115a314bcd23e","entry":"make_name_dict","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/dataloader_feat.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/dataloader_feat.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cbf115a314bcd23e"}},{"code_sha256_prefix":"546678fcbd2854db","entry":"matchmapSim","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/util.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"546678fcbd2854db"}},{"code_sha256_prefix":"2f2ef8ef8d2e3a68","entry":"show_twod","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/noise_robust_asr/asr_experiments/transcribe_whisper.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/noise_robust_asr/asr_experiments/transcribe_whisper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2f2ef8ef8d2e3a68"}},{"code_sha256_prefix":"e529c9641c178fe0","entry":"sinusoids","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"package/whisper-at/whisper_at/model.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/package/whisper-at/whisper_at/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"code_sha256_prefix":"56444fdea1ddc18d","entry":"trunc_normal_","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/models.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"56444fdea1ddc18d"}},{"code_sha256_prefix":"0bed13389f791924","entry":"calc_recalls","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/utilities/util.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/utilities/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0bed13389f791924"}},{"code_sha256_prefix":"7d2dd5f84e2a6da3","entry":"validate","repo":"YuanGongND/whisper-at","repo_kind":"official","path":"src/whisper_at_train/traintest.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/src/whisper_at_train/traintest.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7d2dd5f84e2a6da3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}