{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FVK2EK2UAHTAKVURXNB2XV53E7","short_pith_number":"pith:FVK2EK2U","schema_version":"1.0","canonical_sha256":"2d55a22b5401e6055691bb43abd7bb27ca2a1dd442aae41d77da00bd696a901a","source":{"kind":"arxiv","id":"2301.10606","version":1},"attestation_state":"computed","paper":{"title":"A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Benjamin Peloquin, Changhan Wang, Elizabeth Salesky, Hongyu Gong, Justine Kao, Peng-Jen Chen, Wen-Chin Huang, Yossi Adi","submitted_at":"2023-01-25T14:27:00Z","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"},"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":"2301.10606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T14:27:00Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4a6a430f3d4dd8abec3eb3da11fa661aa4be22a780985e2e8b12d205a55aebe0","abstract_canon_sha256":"0b3e11ced47e6cf6473b33fef434c342b827c8958e1bc28fa9bee29f06242b15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:52.967716Z","signature_b64":"PmoGbp2/hH56wNllu8dfMTUTk/wxJnWvdemOlcnQmU2s5gBMAWG6S+Y49SnjJOqzo3b09RsVOeRGI1nS9BC7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d55a22b5401e6055691bb43abd7bb27ca2a1dd442aae41d77da00bd696a901a","last_reissued_at":"2026-07-05T05:35:52.967267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:52.967267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Benjamin Peloquin, Changhan Wang, Elizabeth Salesky, Hongyu Gong, Justine Kao, Peng-Jen Chen, Wen-Chin Huang, Yossi Adi","submitted_at":"2023-01-25T14:27:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10606","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/2301.10606/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":"2301.10606","created_at":"2026-07-05T05:35:52.967324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10606v1","created_at":"2026-07-05T05:35:52.967324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10606","created_at":"2026-07-05T05:35:52.967324+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVK2EK2UAHTA","created_at":"2026-07-05T05:35:52.967324+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVK2EK2UAHTAKVUR","created_at":"2026-07-05T05:35:52.967324+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVK2EK2U","created_at":"2026-07-05T05:35:52.967324+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/FVK2EK2UAHTAKVURXNB2XV53E7","json":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7.json","graph_json":"https://pith.science/api/pith-number/FVK2EK2UAHTAKVURXNB2XV53E7/graph.json","events_json":"https://pith.science/api/pith-number/FVK2EK2UAHTAKVURXNB2XV53E7/events.json","paper":"https://pith.science/paper/FVK2EK2U"},"agent_actions":{"view_html":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7","download_json":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7.json","view_paper":"https://pith.science/paper/FVK2EK2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10606&json=true","fetch_graph":"https://pith.science/api/pith-number/FVK2EK2UAHTAKVURXNB2XV53E7/graph.json","fetch_events":"https://pith.science/api/pith-number/FVK2EK2UAHTAKVURXNB2XV53E7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7/action/storage_attestation","attest_author":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7/action/author_attestation","sign_citation":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7/action/citation_signature","submit_replication":"https://pith.science/pith/FVK2EK2UAHTAKVURXNB2XV53E7/action/replication_record"}},"created_at":"2026-07-05T05:35:52.967324+00:00","updated_at":"2026-07-05T05:35:52.967324+00:00"}