{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DAESZMTPSBBIV5TLFZ5ACDGA4Q","short_pith_number":"pith:DAESZMTP","schema_version":"1.0","canonical_sha256":"18092cb26f90428af66b2e7a010cc0e41030ca622a874cf166af41879394ccc1","source":{"kind":"arxiv","id":"2505.15667","version":1},"attestation_state":"computed","paper":{"title":"Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Korin Richmond, Nicholas Sanders, Simon King, Yuanchao Li","submitted_at":"2025-05-21T15:44:32Z","abstract_excerpt":"Quantization in SSL speech models (e.g., HuBERT) improves compression and performance in tasks like language modeling, resynthesis, and text-to-speech but often discards prosodic and paralinguistic information (e.g., emotion, prominence). While increasing codebook size mitigates some loss, it inefficiently raises bitrates. We propose Segmentation-Variant Codebooks (SVCs), which quantize speech at distinct linguistic units (frame, phone, word, utterance), factorizing it into multiple streams of segment-specific discrete features. Our results show that SVCs are significantly more effective at pr"},"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":"2505.15667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-21T15:44:32Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"6c122c6d18f0dbab59ba5a3c4de65d7aa6757257909bf0ed92e471b6fa550405","abstract_canon_sha256":"ab03f2762a902a60eeb44b3962aacaab310ba659149e389db1e94c4eab4a5b82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:49.317694Z","signature_b64":"NHunrpuI6lVZjrx5mk5X0nCiEekZ/x+EyjaOMCj/dbr7MAaU8Mt9Yjaw18A+rpWIzJNMWX4LnWbtPs6VHBDlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18092cb26f90428af66b2e7a010cc0e41030ca622a874cf166af41879394ccc1","last_reissued_at":"2026-07-05T11:06:49.317201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:49.317201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Korin Richmond, Nicholas Sanders, Simon King, Yuanchao Li","submitted_at":"2025-05-21T15:44:32Z","abstract_excerpt":"Quantization in SSL speech models (e.g., HuBERT) improves compression and performance in tasks like language modeling, resynthesis, and text-to-speech but often discards prosodic and paralinguistic information (e.g., emotion, prominence). While increasing codebook size mitigates some loss, it inefficiently raises bitrates. We propose Segmentation-Variant Codebooks (SVCs), which quantize speech at distinct linguistic units (frame, phone, word, utterance), factorizing it into multiple streams of segment-specific discrete features. Our results show that SVCs are significantly more effective at pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15667","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/2505.15667/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":"2505.15667","created_at":"2026-07-05T11:06:49.317268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15667v1","created_at":"2026-07-05T11:06:49.317268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15667","created_at":"2026-07-05T11:06:49.317268+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAESZMTPSBBI","created_at":"2026-07-05T11:06:49.317268+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAESZMTPSBBIV5TL","created_at":"2026-07-05T11:06:49.317268+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAESZMTP","created_at":"2026-07-05T11:06:49.317268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15667","citing_title":"Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q","json":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q.json","graph_json":"https://pith.science/api/pith-number/DAESZMTPSBBIV5TLFZ5ACDGA4Q/graph.json","events_json":"https://pith.science/api/pith-number/DAESZMTPSBBIV5TLFZ5ACDGA4Q/events.json","paper":"https://pith.science/paper/DAESZMTP"},"agent_actions":{"view_html":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q","download_json":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q.json","view_paper":"https://pith.science/paper/DAESZMTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15667&json=true","fetch_graph":"https://pith.science/api/pith-number/DAESZMTPSBBIV5TLFZ5ACDGA4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/DAESZMTPSBBIV5TLFZ5ACDGA4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q/action/storage_attestation","attest_author":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q/action/author_attestation","sign_citation":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q/action/citation_signature","submit_replication":"https://pith.science/pith/DAESZMTPSBBIV5TLFZ5ACDGA4Q/action/replication_record"}},"created_at":"2026-07-05T11:06:49.317268+00:00","updated_at":"2026-07-05T11:06:49.317268+00:00"}