{"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/wmcodec-end-to-end-neural-speech-codec-with","title":"WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification","arxiv_id":"2409.12121","date":"2024-09-18","proceeding":null,"authors":["Junzuo Zhou","Jiangyan Yi","Yong Ren","Jianhua Tao","Tao Wang","Chu Yuan Zhang"],"abstract":"Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training processes for the watermark and codec, and insufficient cross-modal information integration, leading to reduced watermark imperceptibility, extraction accuracy, and capacity. To address these issues, we propose WMCodec, the first neural speech codec to jointly train compression-reconstruction and watermark embedding-extraction in an end-to-end manner, optimizing both imperceptibility and extractability of the watermark. Furthermore, We design an iterative Attention Imprint Unit (AIU) for deeper feature integration of watermark and speech, reducing the impact of quantization noise on the watermark. Experimental results show WMCodec outperforms AudioSeal with Encodec in most quality metrics for watermark imperceptibility and consistently exceeds both AudioSeal with Encodec and reinforced TraceableSpeech in extraction accuracy of watermark. At bandwidth of 6 kbps with a watermark capacity of 16 bps, WMCodec maintains over 99% extraction accuracy under common attacks, demonstrating strong robustness.","url_abs":"https://arxiv.org/abs/2409.12121v3","url_pdf":"https://arxiv.org/pdf/2409.12121v3.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":"wmcodec-end-to-end-neural-speech-codec-with","repo_url":"https://github.com/zjzser/wmcodec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.12121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12121"}},"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/zjzser/wmcodec","reach":{"status":"ok"}}],"summary":{"ran_violates":2,"ran":4,"ran_draft_wrong":2,"unverified":7},"by_repo_kind":{"official":{"samples":15,"ran":8,"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":15,"samples":[{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"zjzser/wmcodec","repo_kind":"official","path":"EMT.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/EMT.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"7137577cbef51217","entry":"discriminator_loss","repo":"zjzser/wmcodec","repo_kind":"official","path":"models.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7137577cbef51217"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"zjzser/wmcodec","repo_kind":"official","path":"EMT.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/EMT.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"zjzser/wmcodec","repo_kind":"official","path":"models.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"zjzser/wmcodec","repo_kind":"official","path":"models.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a9d74439d969cfd"}},{"code_sha256_prefix":"19c9fe23dc000c61","entry":"load_checkpoint","repo":"zjzser/wmcodec","repo_kind":"official","path":"inference-at.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/inference-at.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"19c9fe23dc000c61"}},{"code_sha256_prefix":"8043eaefe4c09c1f","entry":"load_wav","repo":"zjzser/wmcodec","repo_kind":"official","path":"meldataset.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/meldataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8043eaefe4c09c1f"}},{"code_sha256_prefix":"404632cb4f4669da","entry":"scan_checkpoint","repo":"zjzser/wmcodec","repo_kind":"official","path":"inference-at.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/inference-at.py","link_basis":"harvester_set","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":"404632cb4f4669da"}},{"code_sha256_prefix":"6c82cd3d9b6dba51","entry":"apply_parametrization_norm","repo":"zjzser/wmcodec","repo_kind":"official","path":"modules/conv.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/modules/conv.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c82cd3d9b6dba51"}},{"code_sha256_prefix":"e56401f8aa027f99","entry":"cache_fn","repo":"zjzser/wmcodec","repo_kind":"official","path":"EMT.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/EMT.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e56401f8aa027f99"}},{"code_sha256_prefix":"5969591b5acad09f","entry":"create_sin_embedding","repo":"zjzser/wmcodec","repo_kind":"official","path":"modules/transformer.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/modules/transformer.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5969591b5acad09f"}},{"code_sha256_prefix":"be031b15a988a556","entry":"dynamic_range_compression","repo":"zjzser/wmcodec","repo_kind":"official","path":"meldataset.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/meldataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be031b15a988a556"}},{"code_sha256_prefix":"9e30e7d510c9d341","entry":"dynamic_range_decompression","repo":"zjzser/wmcodec","repo_kind":"official","path":"meldataset.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/meldataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e30e7d510c9d341"}},{"code_sha256_prefix":"8d9aa381c6147164","entry":"get_extra_padding_for_conv1d","repo":"zjzser/wmcodec","repo_kind":"official","path":"modules/conv.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/modules/conv.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d9aa381c6147164"}},{"code_sha256_prefix":"9b33ed59d8d8736e","entry":"get_norm_module","repo":"zjzser/wmcodec","repo_kind":"official","path":"modules/conv.py","file_url":"https://github.com/zjzser/wmcodec/blob/HEAD/modules/conv.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b33ed59d8d8736e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}