{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRJ2IHEVIQFQUOOWQPDL557XYX","short_pith_number":"pith:BRJ2IHEV","schema_version":"1.0","canonical_sha256":"0c53a41c95440b0a39d683c6bef7f7c5cedef16c590fa29ad5bdc5f2e2a46fbb","source":{"kind":"arxiv","id":"2409.01995","version":4},"attestation_state":"computed","paper":{"title":"vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Hankun Wang, Junjie Li, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo, Zhihan Li","submitted_at":"2024-09-03T15:41:07Z","abstract_excerpt":"We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice conversion (VC). We use discrete tokens from speech self-supervised models as the content features of source speech, and treat VC as a prompted vocoding task. To amend the loss of speaker timbre in the content tokens, vec2wav 2.0 utilizes the WavLM features to provide strong timbre-dependent information. A novel adaptive Snake activation function is proposed to better incorporate timbre into the waveform reconstruction process. In this way, vec2wav 2.0 learns to alter the speaker timbre appropriately given differ"},"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":"2409.01995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-03T15:41:07Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"a952ac36ce6ef8ab6ffe57736f935cc0b4b551e548ef00c85f9d23eb38c26941","abstract_canon_sha256":"0e64e937ffd096bd54ce10f43d7b8839669ad67ac0596732d1c74c37ac9e3162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:00.023914Z","signature_b64":"JErWIidsOE0KiHjKdS7H8qXnYDeOEqlii8GgWSARXsA5rdpuBFBUssmjb9gNeTs8tGGT9Ym4k3KQ5nfg65RxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c53a41c95440b0a39d683c6bef7f7c5cedef16c590fa29ad5bdc5f2e2a46fbb","last_reissued_at":"2026-07-05T11:09:00.023433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:00.023433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Hankun Wang, Junjie Li, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo, Zhihan Li","submitted_at":"2024-09-03T15:41:07Z","abstract_excerpt":"We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice conversion (VC). We use discrete tokens from speech self-supervised models as the content features of source speech, and treat VC as a prompted vocoding task. To amend the loss of speaker timbre in the content tokens, vec2wav 2.0 utilizes the WavLM features to provide strong timbre-dependent information. A novel adaptive Snake activation function is proposed to better incorporate timbre into the waveform reconstruction process. In this way, vec2wav 2.0 learns to alter the speaker timbre appropriately given differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01995","kind":"arxiv","version":4},"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/2409.01995/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":"2409.01995","created_at":"2026-07-05T11:09:00.023490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01995v4","created_at":"2026-07-05T11:09:00.023490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01995","created_at":"2026-07-05T11:09:00.023490+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRJ2IHEVIQFQ","created_at":"2026-07-05T11:09:00.023490+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRJ2IHEVIQFQUOOW","created_at":"2026-07-05T11:09:00.023490+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRJ2IHEV","created_at":"2026-07-05T11:09:00.023490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21157","citing_title":"SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05678","citing_title":"Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30356","citing_title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12456","citing_title":"X-VC: Zero-shot Streaming Voice Conversion in Codec Space","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX","json":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX.json","graph_json":"https://pith.science/api/pith-number/BRJ2IHEVIQFQUOOWQPDL557XYX/graph.json","events_json":"https://pith.science/api/pith-number/BRJ2IHEVIQFQUOOWQPDL557XYX/events.json","paper":"https://pith.science/paper/BRJ2IHEV"},"agent_actions":{"view_html":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX","download_json":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX.json","view_paper":"https://pith.science/paper/BRJ2IHEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01995&json=true","fetch_graph":"https://pith.science/api/pith-number/BRJ2IHEVIQFQUOOWQPDL557XYX/graph.json","fetch_events":"https://pith.science/api/pith-number/BRJ2IHEVIQFQUOOWQPDL557XYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX/action/storage_attestation","attest_author":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX/action/author_attestation","sign_citation":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX/action/citation_signature","submit_replication":"https://pith.science/pith/BRJ2IHEVIQFQUOOWQPDL557XYX/action/replication_record"}},"created_at":"2026-07-05T11:09:00.023490+00:00","updated_at":"2026-07-05T11:09:00.023490+00:00"}