{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YACCSPHP7SF4WN7XW2VI6DVS7K","short_pith_number":"pith:YACCSPHP","schema_version":"1.0","canonical_sha256":"c004293ceffc8bcb37f7b6aa8f0eb2fa9ece1a043bc944b153536694b99f1f69","source":{"kind":"arxiv","id":"2607.01238","version":1},"attestation_state":"computed","paper":{"title":"SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Mark Hasegawa-Johnson, Priyam Mazumdar, Steven Guo, Volodymyr Kindratenko, Yurii Halychanskyi","submitted_at":"2026-05-01T17:46:18Z","abstract_excerpt":"Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling. While phonemes address the one-to-many mapping between text and acoustics, they rely on grapheme-to-phoneme (G2P) systems that fail to capture speaker-specific acoustic variation. Prior work demonstrates that grapheme-based models outperform phoneme-based systems at scale, but not in low-resource settings.\n  In this paper, we propose SPARCLE, a speaker-aware grapheme representation model that enriches characters with their precise acoustic realizations. SPARCLE is trained with a contrasti"},"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":"2607.01238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T17:46:18Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"a3ca288eb36a94ac3b7db2d54db85e358e5c73c2d8c9d43d7ee44f3131ca32f4","abstract_canon_sha256":"43c9ba74ff1e5f5ba3a5364b75371ae60d6a78fe89f1eee7b814b34605cf32b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:55.032017Z","signature_b64":"0f7eq0cvY9NqtubG4o2da8FnZcrUlthn1IpP8u3KUsCAhV2hL8M4SPI5tTcwrGSqIwkXoKAlgI9kSeAisQoGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c004293ceffc8bcb37f7b6aa8f0eb2fa9ece1a043bc944b153536694b99f1f69","last_reissued_at":"2026-07-03T00:16:55.031597Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:55.031597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Mark Hasegawa-Johnson, Priyam Mazumdar, Steven Guo, Volodymyr Kindratenko, Yurii Halychanskyi","submitted_at":"2026-05-01T17:46:18Z","abstract_excerpt":"Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling. While phonemes address the one-to-many mapping between text and acoustics, they rely on grapheme-to-phoneme (G2P) systems that fail to capture speaker-specific acoustic variation. Prior work demonstrates that grapheme-based models outperform phoneme-based systems at scale, but not in low-resource settings.\n  In this paper, we propose SPARCLE, a speaker-aware grapheme representation model that enriches characters with their precise acoustic realizations. SPARCLE is trained with a contrasti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01238","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/2607.01238/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":"2607.01238","created_at":"2026-07-03T00:16:55.031654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01238v1","created_at":"2026-07-03T00:16:55.031654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01238","created_at":"2026-07-03T00:16:55.031654+00:00"},{"alias_kind":"pith_short_12","alias_value":"YACCSPHP7SF4","created_at":"2026-07-03T00:16:55.031654+00:00"},{"alias_kind":"pith_short_16","alias_value":"YACCSPHP7SF4WN7X","created_at":"2026-07-03T00:16:55.031654+00:00"},{"alias_kind":"pith_short_8","alias_value":"YACCSPHP","created_at":"2026-07-03T00:16:55.031654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.01238","citing_title":"SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K","json":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K.json","graph_json":"https://pith.science/api/pith-number/YACCSPHP7SF4WN7XW2VI6DVS7K/graph.json","events_json":"https://pith.science/api/pith-number/YACCSPHP7SF4WN7XW2VI6DVS7K/events.json","paper":"https://pith.science/paper/YACCSPHP"},"agent_actions":{"view_html":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K","download_json":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K.json","view_paper":"https://pith.science/paper/YACCSPHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01238&json=true","fetch_graph":"https://pith.science/api/pith-number/YACCSPHP7SF4WN7XW2VI6DVS7K/graph.json","fetch_events":"https://pith.science/api/pith-number/YACCSPHP7SF4WN7XW2VI6DVS7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K/action/storage_attestation","attest_author":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K/action/author_attestation","sign_citation":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K/action/citation_signature","submit_replication":"https://pith.science/pith/YACCSPHP7SF4WN7XW2VI6DVS7K/action/replication_record"}},"created_at":"2026-07-03T00:16:55.031654+00:00","updated_at":"2026-07-03T00:16:55.031654+00:00"}