{"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/sound-localization-by-self-supervised-time","title":"Sound Localization by Self-Supervised Time Delay Estimation","arxiv_id":"2204.12489","date":"2022-04-26","proceeding":null,"authors":["Ziyang Chen","David F. Fouhey","Andrew Owens"],"abstract":"Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound's time delay requires finding correspondences between the signals recorded by each microphone. We propose to learn these correspondences through self-supervision, drawing on recent techniques from visual tracking. We adapt the contrastive random walk of Jabri et al. to learn a cycle-consistent representation from unlabeled stereo sounds, resulting in a model that performs on par with supervised methods on \"in the wild\" internet recordings. We also propose a multimodal contrastive learning model that solves a visually-guided localization task: estimating the time delay for a particular person in a multi-speaker mixture, given a visual representation of their face. Project site: https://ificl.github.io/stereocrw/","url_abs":"https://arxiv.org/abs/2204.12489v3","url_pdf":"https://arxiv.org/pdf/2204.12489v3.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":"sound-localization-by-self-supervised-time","repo_url":"https://github.com/IFICL/stereocrw","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.12489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.12489"}},"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/IFICL/stereocrw","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":16},"by_repo_kind":{"official":{"samples":16,"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":"90ce9429d8e138ca","entry":"angle","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/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":"90ce9429d8e138ca"}},{"code_sha256_prefix":"985be22f95033ef0","entry":"apply_cmap","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/vis_utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/vis_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":"985be22f95033ef0"}},{"code_sha256_prefix":"3da38a399d02010a","entry":"binary_acc","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/torch_utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/torch_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":"3da38a399d02010a"}},{"code_sha256_prefix":"e1dc20ea343147aa","entry":"calc_acc","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/torch_utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/torch_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":"e1dc20ea343147aa"}},{"code_sha256_prefix":"85e99894dc6a3ab1","entry":"clip_rescale","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/vis_utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/vis_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":"85e99894dc6a3ab1"}},{"code_sha256_prefix":"954ba75869c341e4","entry":"cmap_im","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/vis_utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/vis_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":"954ba75869c341e4"}},{"code_sha256_prefix":"3cecb8e4ec547c9c","entry":"eval_regression","repo":"IFICL/stereocrw","repo_kind":"official","path":"vis_scripts/eval_itd_by_itd.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/vis_scripts/eval_itd_by_itd.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":"3cecb8e4ec547c9c"}},{"code_sha256_prefix":"8f4555ec07aef089","entry":"inference","repo":"IFICL/stereocrw","repo_kind":"official","path":"vis_scripts/eval_itd_by_itd.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/vis_scripts/eval_itd_by_itd.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":"8f4555ec07aef089"}},{"code_sha256_prefix":"30a8feb0ae31dd2f","entry":"init_args","repo":"IFICL/stereocrw","repo_kind":"official","path":"config/config.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/config/config.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":"30a8feb0ae31dd2f"}},{"code_sha256_prefix":"dd477c377ef9e596","entry":"load_model","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/torch_utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/torch_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":"dd477c377ef9e596"}},{"code_sha256_prefix":"cb41f906fb41033a","entry":"load_sound","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/sound.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/sound.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":"cb41f906fb41033a"}},{"code_sha256_prefix":"1257ffc2d2e10d60","entry":"normalize_rms","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/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":"1257ffc2d2e10d60"}},{"code_sha256_prefix":"9282d9cd4bf5682e","entry":"normalize_rms_np","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/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":"9282d9cd4bf5682e"}},{"code_sha256_prefix":"d276952abad5059f","entry":"stft_frame_length","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/sourcesep.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/sourcesep.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":"d276952abad5059f"}},{"code_sha256_prefix":"3c5b0d2377733d6f","entry":"stft_frame_step","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/sourcesep.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/sourcesep.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":"3c5b0d2377733d6f"}},{"code_sha256_prefix":"28487c00cd7b97ce","entry":"stft_num_fft","repo":"IFICL/stereocrw","repo_kind":"official","path":"utils/sourcesep.py","file_url":"https://github.com/IFICL/stereocrw/blob/HEAD/utils/sourcesep.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":"28487c00cd7b97ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}