{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DULKL4IFOOR3VKFVBCV3DESCPU","short_pith_number":"pith:DULKL4IF","schema_version":"1.0","canonical_sha256":"1d16a5f10573a3baa8b508abb192427d34b7671839a16ad64b07057f9935a398","source":{"kind":"arxiv","id":"2406.04840","version":3},"attestation_state":"computed","paper":{"title":"TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chu Yuan Zhang, Jiangyan Yi, Jianhua Tao, Junzuo Zhou, Tao Wang, Ye Bai, Yong Ren, Zhengqi Wen","submitted_at":"2024-06-07T11:13:03Z","abstract_excerpt":"Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a process that hurts both speech quality and watermark imperceptibility. In addition, these approaches are limited in robustness and flexibility. To address these problems, we propose TraceableSpeech, a novel TTS model that directly generates watermarked speech, improving watermark imperceptibility and speech quality. Furthermore, We design the frame-wise impri"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.04840","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-07T11:13:03Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"122a76c0c73961c070e8fe0f8ef7de94908046d351501fdbf9667787ffb2e5fa","abstract_canon_sha256":"e6c540fe3535d7d54f0eb261698a09aa80cd93658abd970efc49054b2bae2205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:49.756273Z","signature_b64":"6+DyQ6BZLa/G5mHzl2PkVY0TviKZejyHwndk1TAjrOSwz0RKVMxf0t3X2i5/28a51qNeJ4x4u7xkj76gR+qrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d16a5f10573a3baa8b508abb192427d34b7671839a16ad64b07057f9935a398","last_reissued_at":"2026-07-05T09:35:49.755728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:49.755728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chu Yuan Zhang, Jiangyan Yi, Jianhua Tao, Junzuo Zhou, Tao Wang, Ye Bai, Yong Ren, Zhengqi Wen","submitted_at":"2024-06-07T11:13:03Z","abstract_excerpt":"Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a process that hurts both speech quality and watermark imperceptibility. In addition, these approaches are limited in robustness and flexibility. To address these problems, we propose TraceableSpeech, a novel TTS model that directly generates watermarked speech, improving watermark imperceptibility and speech quality. Furthermore, We design the frame-wise impri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04840","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.04840/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.04840","created_at":"2026-07-05T09:35:49.755800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04840v3","created_at":"2026-07-05T09:35:49.755800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04840","created_at":"2026-07-05T09:35:49.755800+00:00"},{"alias_kind":"pith_short_12","alias_value":"DULKL4IFOOR3","created_at":"2026-07-05T09:35:49.755800+00:00"},{"alias_kind":"pith_short_16","alias_value":"DULKL4IFOOR3VKFV","created_at":"2026-07-05T09:35:49.755800+00:00"},{"alias_kind":"pith_short_8","alias_value":"DULKL4IF","created_at":"2026-07-05T09:35:49.755800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01515","citing_title":"MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU","json":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU.json","graph_json":"https://pith.science/api/pith-number/DULKL4IFOOR3VKFVBCV3DESCPU/graph.json","events_json":"https://pith.science/api/pith-number/DULKL4IFOOR3VKFVBCV3DESCPU/events.json","paper":"https://pith.science/paper/DULKL4IF"},"agent_actions":{"view_html":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU","download_json":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU.json","view_paper":"https://pith.science/paper/DULKL4IF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04840&json=true","fetch_graph":"https://pith.science/api/pith-number/DULKL4IFOOR3VKFVBCV3DESCPU/graph.json","fetch_events":"https://pith.science/api/pith-number/DULKL4IFOOR3VKFVBCV3DESCPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU/action/storage_attestation","attest_author":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU/action/author_attestation","sign_citation":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU/action/citation_signature","submit_replication":"https://pith.science/pith/DULKL4IFOOR3VKFVBCV3DESCPU/action/replication_record"}},"created_at":"2026-07-05T09:35:49.755800+00:00","updated_at":"2026-07-05T09:35:49.755800+00:00"}