{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5RGITEMCHMP3HVF4FPL3EUGXYL","short_pith_number":"pith:5RGITEMC","schema_version":"1.0","canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","source":{"kind":"arxiv","id":"2606.21888","version":1},"attestation_state":"computed","paper":{"title":"ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung, Shujie Hu","submitted_at":"2026-06-20T05:19:07Z","abstract_excerpt":"Neural speech codecs efficiently compress speech and have become a foundation for speech generation, but they are typically learned as holistic representations that intertwine linguistic content, speaker identity, and prosody. While this design is effective for zero-shot voice cloning, it hinders downstream tasks that require prosody preservation or transfer, such as voice conversion. To address this, we introduce ProsoCodec, a prosody-oriented speech codec that models prosody as a conditional residual rather than as a disentangled stream. Specifically, by conditioning both the encoder and dec"},"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":"2606.21888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T05:19:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0b88669d0dddd6ccf6275ae88e6d022d5112b85be96f96ea2f409217f1bf968f","abstract_canon_sha256":"cc391a8ff2a21053303df5895d65e9f1e435640a06968519e52f83b2458e95b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:01.960080Z","signature_b64":"1CZPjaGg7UlaBAaxax2ngojtcRh+iNj5n0VCCOSzGMQHJqv+M+925e5ekFrtzLJ69VAIC1Ty4NMNel3EXZkKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","last_reissued_at":"2026-06-23T02:13:01.959699Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:01.959699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung, Shujie Hu","submitted_at":"2026-06-20T05:19:07Z","abstract_excerpt":"Neural speech codecs efficiently compress speech and have become a foundation for speech generation, but they are typically learned as holistic representations that intertwine linguistic content, speaker identity, and prosody. While this design is effective for zero-shot voice cloning, it hinders downstream tasks that require prosody preservation or transfer, such as voice conversion. To address this, we introduce ProsoCodec, a prosody-oriented speech codec that models prosody as a conditional residual rather than as a disentangled stream. Specifically, by conditioning both the encoder and dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21888","kind":"arxiv","version":1},"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/2606.21888/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":"2606.21888","created_at":"2026-06-23T02:13:01.959761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21888v1","created_at":"2026-06-23T02:13:01.959761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21888","created_at":"2026-06-23T02:13:01.959761+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RGITEMCHMP3","created_at":"2026-06-23T02:13:01.959761+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RGITEMCHMP3HVF4","created_at":"2026-06-23T02:13:01.959761+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RGITEMC","created_at":"2026-06-23T02:13:01.959761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.21888","citing_title":"ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL","json":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL.json","graph_json":"https://pith.science/api/pith-number/5RGITEMCHMP3HVF4FPL3EUGXYL/graph.json","events_json":"https://pith.science/api/pith-number/5RGITEMCHMP3HVF4FPL3EUGXYL/events.json","paper":"https://pith.science/paper/5RGITEMC"},"agent_actions":{"view_html":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL","download_json":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL.json","view_paper":"https://pith.science/paper/5RGITEMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21888&json=true","fetch_graph":"https://pith.science/api/pith-number/5RGITEMCHMP3HVF4FPL3EUGXYL/graph.json","fetch_events":"https://pith.science/api/pith-number/5RGITEMCHMP3HVF4FPL3EUGXYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/action/storage_attestation","attest_author":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/action/author_attestation","sign_citation":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/action/citation_signature","submit_replication":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/action/replication_record"}},"created_at":"2026-06-23T02:13:01.959761+00:00","updated_at":"2026-06-23T02:13:01.959761+00:00"}