{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ","short_pith_number":"pith:SHWJ7X7P","schema_version":"1.0","canonical_sha256":"91ec9fdfefdb60fcfaa19209ece10304292637e962d41b2a320627448db90e61","source":{"kind":"arxiv","id":"2603.28737","version":2},"attestation_state":"computed","paper":{"title":"ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anuj Diwan, David Harwath, Eunsol Choi","submitted_at":"2026-03-30T17:50:07Z","abstract_excerpt":"We introduce ParaSpeechCLAP, a family of dual-encoder models that map speech and text style captions into a shared embedding space, supporting rich intrinsic (speaker-level) and situational (utterance-level) descriptors, such as pitch, texture, and emotion, beyond the narrow set handled by existing models. We train separate Intrinsic and Situational models alongside a unified Combined model, finding that specialized models are stronger on individual style dimensions while the unified model excels on compositional evaluation. We further show that ParaSpeechCLAP-Intrinsic benefits from an additi"},"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":"2603.28737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-30T17:50:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"0af5c8a9ffd9ddb2a293d1f963cfaff662e69e01232feca046825f6b6c8a315a","abstract_canon_sha256":"cb9c9db5fed56ee398f3fe03c231487438d761a193982ec17172fa62a6feba92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:23.168460Z","signature_b64":"ldir+OZ6cQZZyG1umfKB0+J2m7S8ZWx59ezWBBC7nDrjw8VhgmJi5REK5AT95utS/W7R4dmr9HBWwUF/fMijAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91ec9fdfefdb60fcfaa19209ece10304292637e962d41b2a320627448db90e61","last_reissued_at":"2026-06-23T02:13:23.168018Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:23.168018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anuj Diwan, David Harwath, Eunsol Choi","submitted_at":"2026-03-30T17:50:07Z","abstract_excerpt":"We introduce ParaSpeechCLAP, a family of dual-encoder models that map speech and text style captions into a shared embedding space, supporting rich intrinsic (speaker-level) and situational (utterance-level) descriptors, such as pitch, texture, and emotion, beyond the narrow set handled by existing models. We train separate Intrinsic and Situational models alongside a unified Combined model, finding that specialized models are stronger on individual style dimensions while the unified model excels on compositional evaluation. We further show that ParaSpeechCLAP-Intrinsic benefits from an additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28737","kind":"arxiv","version":2},"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/2603.28737/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":"2603.28737","created_at":"2026-06-23T02:13:23.168075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.28737v2","created_at":"2026-06-23T02:13:23.168075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28737","created_at":"2026-06-23T02:13:23.168075+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHWJ7X7P3NQP","created_at":"2026-06-23T02:13:23.168075+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHWJ7X7P3NQPZ6VB","created_at":"2026-06-23T02:13:23.168075+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHWJ7X7P","created_at":"2026-06-23T02:13:23.168075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ","json":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ.json","graph_json":"https://pith.science/api/pith-number/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/graph.json","events_json":"https://pith.science/api/pith-number/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/events.json","paper":"https://pith.science/paper/SHWJ7X7P"},"agent_actions":{"view_html":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ","download_json":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ.json","view_paper":"https://pith.science/paper/SHWJ7X7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.28737&json=true","fetch_graph":"https://pith.science/api/pith-number/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/action/storage_attestation","attest_author":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/action/author_attestation","sign_citation":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/action/citation_signature","submit_replication":"https://pith.science/pith/SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ/action/replication_record"}},"created_at":"2026-06-23T02:13:23.168075+00:00","updated_at":"2026-06-23T02:13:23.168075+00:00"}