{"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-codec-augmentation-for-robust","title":"Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis","arxiv_id":"2409.13382","date":"2024-09-20","proceeding":null,"authors":["Lauri Juvela","Xin Wang"],"abstract":"Automatic detection of synthetic speech is becoming increasingly important as current synthesis methods are both near indistinguishable from human speech and widely accessible to the public. Audio watermarking and other active disclosure methods of are attracting research activity, as they can complement traditional deepfake defenses based on passive detection. In both active and passive detection, robustness is of major interest. Traditional audio watermarks are particularly susceptible to removal attacks by audio codec application. Most generated speech and audio content released into the wild passes through an audio codec purely as a distribution method. We recently proposed collaborative watermarking as method for making generated speech more easily detectable over a noisy but differentiable transmission channel. This paper extends the channel augmentation to work with non-differentiable traditional audio codecs and neural audio codecs and evaluates transferability and effect of codec bitrate over various configurations. The results show that collaborative watermarking can be reliably augmented by black-box audio codecs using a waveform-domain straight-through-estimator for gradient approximation. Furthermore, that results show that channel augmentation with a neural audio codec transfers well to traditional codecs. Listening tests demonstrate collaborative watermarking incurs negligible perceptual degradation with high bitrate codecs or DAC at 8kbps.","url_abs":"https://arxiv.org/abs/2409.13382v1","url_pdf":"https://arxiv.org/pdf/2409.13382v1.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-codec-augmentation-for-robust","repo_url":"https://github.com/ljuvela/collaborative-watermarking-with-codecs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"face-swapping","task_name":"Face Swapping"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[{"method_slug":"dac","method_name":"DAC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.13382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13382"}},"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/ljuvela/collaborative-watermarking-with-codecs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"047149960a2fd5d6","entry":"compute_det_curve","repo":"ljuvela/collaborative-watermarking-with-codecs","repo_kind":"official","path":"src/collaborative_watermarking/metrics.py","file_url":"https://github.com/ljuvela/collaborative-watermarking-with-codecs/blob/HEAD/src/collaborative_watermarking/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"047149960a2fd5d6"}},{"code_sha256_prefix":"6c660ac679abd4e2","entry":"compute_eer","repo":"ljuvela/collaborative-watermarking-with-codecs","repo_kind":"official","path":"src/collaborative_watermarking/metrics.py","file_url":"https://github.com/ljuvela/collaborative-watermarking-with-codecs/blob/HEAD/src/collaborative_watermarking/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c660ac679abd4e2"}},{"code_sha256_prefix":"be031b15a988a556","entry":"dynamic_range_compression","repo":"ljuvela/collaborative-watermarking-with-codecs","repo_kind":"official","path":"src/collaborative_watermarking/meldataset.py","file_url":"https://github.com/ljuvela/collaborative-watermarking-with-codecs/blob/HEAD/src/collaborative_watermarking/meldataset.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":"be031b15a988a556"}},{"code_sha256_prefix":"9e30e7d510c9d341","entry":"dynamic_range_decompression","repo":"ljuvela/collaborative-watermarking-with-codecs","repo_kind":"official","path":"src/collaborative_watermarking/meldataset.py","file_url":"https://github.com/ljuvela/collaborative-watermarking-with-codecs/blob/HEAD/src/collaborative_watermarking/meldataset.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":"9e30e7d510c9d341"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}