{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OBLHSIJRVGMKKNDV2MOH2ZSHT4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"000053e04b55b0a69ea31e07cbf6ddae3100394c1611eaf8d84b5cc0616b55dc","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-17T14:47:05Z","title_canon_sha256":"375ced365246a84cbaafde133e2c81652466560447d4204647f125c81fb0ac2c"},"schema_version":"1.0","source":{"id":"2408.09215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09215","created_at":"2026-07-05T08:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09215v1","created_at":"2026-07-05T08:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09215","created_at":"2026-07-05T08:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"OBLHSIJRVGMK","created_at":"2026-07-05T08:56:29Z"},{"alias_kind":"pith_short_16","alias_value":"OBLHSIJRVGMKKNDV","created_at":"2026-07-05T08:56:29Z"},{"alias_kind":"pith_short_8","alias_value":"OBLHSIJR","created_at":"2026-07-05T08:56:29Z"}],"graph_snapshots":[{"event_id":"sha256:318a3956799267a06f6afc38c608209257f82a9e29821ad565e98e92be21bc08","target":"graph","created_at":"2026-07-05T08:56:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.09215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, a common approach in many speech processing tasks is to leverage large scale pre-trained models by fine-tuning them on in-domain data for a particular application. Yet obtaining even a small amount of such data can be problematic, especially for sensitive domains and conversational speech scenarios, due to both privacy issues and annotation costs. To address this, synthetic data generation using single speaker datasets has been employed. Yet, for multi-speaker cases, such an approach often requires extensive manual effort and is prone to domain mismatches. In this work, we propose a","authors_text":"Jordan Darefsky, Samuele Cornell, Shinji Watanabe, Zhiyao Duan","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-17T14:47:05Z","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09215","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:89dae0ff3737d4ea97a1d32e0e6b5f6fece7e987588de975ace062d1e851a39e","target":"record","created_at":"2026-07-05T08:56:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"000053e04b55b0a69ea31e07cbf6ddae3100394c1611eaf8d84b5cc0616b55dc","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-17T14:47:05Z","title_canon_sha256":"375ced365246a84cbaafde133e2c81652466560447d4204647f125c81fb0ac2c"},"schema_version":"1.0","source":{"id":"2408.09215","kind":"arxiv","version":1}},"canonical_sha256":"7056792131a998a53475d31c7d66479f34c591b548bb907037a495f097adc477","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7056792131a998a53475d31c7d66479f34c591b548bb907037a495f097adc477","first_computed_at":"2026-07-05T08:56:29.789442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:29.789442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5ZulqcLDzJEj0pdgn8K0sYhJpCaiPWcsG50Dfa4A5tcbsd7/xi2l/Dqzx/vPoAHGP5AiQu22n1Tvxs5hU5pAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:29.789800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89dae0ff3737d4ea97a1d32e0e6b5f6fece7e987588de975ace062d1e851a39e","sha256:318a3956799267a06f6afc38c608209257f82a9e29821ad565e98e92be21bc08"],"state_sha256":"801747570499a0bfc1f154ad79863664f9c0206453741855a0e620353c5aac05"}