{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FVK2EK2UAHTAKVURXNB2XV53E7","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":"0b3e11ced47e6cf6473b33fef434c342b827c8958e1bc28fa9bee29f06242b15","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T14:27:00Z","title_canon_sha256":"4a6a430f3d4dd8abec3eb3da11fa661aa4be22a780985e2e8b12d205a55aebe0"},"schema_version":"1.0","source":{"id":"2301.10606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10606","created_at":"2026-07-05T05:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10606v1","created_at":"2026-07-05T05:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10606","created_at":"2026-07-05T05:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"FVK2EK2UAHTA","created_at":"2026-07-05T05:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"FVK2EK2UAHTAKVUR","created_at":"2026-07-05T05:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"FVK2EK2U","created_at":"2026-07-05T05:35:52Z"}],"graph_snapshots":[{"event_id":"sha256:300e912c0eed65c66c33c3e1b715c0656426616bb40ed3ddb3283a1700378194","target":"graph","created_at":"2026-07-05T05:35:52Z","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/2301.10606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive speech-to-speech translation (S2ST) aims to transfer prosodic attributes of source speech to target speech while maintaining translation accuracy. Existing research in expressive S2ST is limited, typically focusing on a single expressivity aspect at a time. Likewise, this research area lacks standard evaluation protocols and well-curated benchmark datasets. In this work, we propose a holistic cascade system for expressive S2ST, combining multiple prosody transfer techniques previously considered only in isolation. We curate a benchmark expressivity test set in the TV series domain a","authors_text":"Ann Lee, Benjamin Peloquin, Changhan Wang, Elizabeth Salesky, Hongyu Gong, Justine Kao, Peng-Jen Chen, Wen-Chin Huang, Yossi Adi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T14:27:00Z","title":"A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10606","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":"sha256:8a69d2eb421e4a20bd5e0416dfd025a2dadc089501a051cf3b957133cad3f96c","target":"record","created_at":"2026-07-05T05:35:52Z","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":"0b3e11ced47e6cf6473b33fef434c342b827c8958e1bc28fa9bee29f06242b15","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T14:27:00Z","title_canon_sha256":"4a6a430f3d4dd8abec3eb3da11fa661aa4be22a780985e2e8b12d205a55aebe0"},"schema_version":"1.0","source":{"id":"2301.10606","kind":"arxiv","version":1}},"canonical_sha256":"2d55a22b5401e6055691bb43abd7bb27ca2a1dd442aae41d77da00bd696a901a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d55a22b5401e6055691bb43abd7bb27ca2a1dd442aae41d77da00bd696a901a","first_computed_at":"2026-07-05T05:35:52.967267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:35:52.967267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PmoGbp2/hH56wNllu8dfMTUTk/wxJnWvdemOlcnQmU2s5gBMAWG6S+Y49SnjJOqzo3b09RsVOeRGI1nS9BC7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:35:52.967716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.10606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a69d2eb421e4a20bd5e0416dfd025a2dadc089501a051cf3b957133cad3f96c","sha256:300e912c0eed65c66c33c3e1b715c0656426616bb40ed3ddb3283a1700378194"],"state_sha256":"0c930061f66ffb9c39172cf02a2bfbcba5fd0e69e4d46141e6d5c07a8cba808d"}