{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:26LVMWNIBFTQE5RT4DZOXWDSFI","short_pith_number":"pith:26LVMWNI","schema_version":"1.0","canonical_sha256":"d7975659a80967027633e0f2ebd8722a32006a06cc6a6d363d861a2906766e81","source":{"kind":"arxiv","id":"2205.12523","version":2},"attestation_state":"computed","paper":{"title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huadai Liu, Jinglin Liu, Jinzheng He, Lichao Zhang, Rongjie Huang, Yi Ren, Zhou Zhao","submitted_at":"2022-05-25T06:34:14Z","abstract_excerpt":"Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in speech representation learning. Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while still facing the following challenges: 1) Acoustic multimodality: the discrete units derived from speech with same content could be indeterministic due to the acoustic property (e.g., rhythm, pitch, and energy), which causes deterioration of translation accuracy; 2) high latency: current S2ST systems"},"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":"2205.12523","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T06:34:14Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1d28c2cf3e2ea6ae26c234c8a35b2c625a982bd7270ee89a5819bd7d828ba157","abstract_canon_sha256":"db7cf7e6b07d989f74e64b1aa5891aabc2087c561322053431d6d22478490f42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:15.546083Z","signature_b64":"JyTtxgq6cghRL3UKUmudw5SKI9uhbS6AwDq0uiSxK81U2QPTby1sylC3o6Do42Lk3DQEEUXb9vAgP2XRkBq0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7975659a80967027633e0f2ebd8722a32006a06cc6a6d363d861a2906766e81","last_reissued_at":"2026-07-05T05:47:15.545596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:15.545596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huadai Liu, Jinglin Liu, Jinzheng He, Lichao Zhang, Rongjie Huang, Yi Ren, Zhou Zhao","submitted_at":"2022-05-25T06:34:14Z","abstract_excerpt":"Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in speech representation learning. Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while still facing the following challenges: 1) Acoustic multimodality: the discrete units derived from speech with same content could be indeterministic due to the acoustic property (e.g., rhythm, pitch, and energy), which causes deterioration of translation accuracy; 2) high latency: current S2ST systems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12523","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/2205.12523/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":"2205.12523","created_at":"2026-07-05T05:47:15.545669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12523v2","created_at":"2026-07-05T05:47:15.545669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12523","created_at":"2026-07-05T05:47:15.545669+00:00"},{"alias_kind":"pith_short_12","alias_value":"26LVMWNIBFTQ","created_at":"2026-07-05T05:47:15.545669+00:00"},{"alias_kind":"pith_short_16","alias_value":"26LVMWNIBFTQE5RT","created_at":"2026-07-05T05:47:15.545669+00:00"},{"alias_kind":"pith_short_8","alias_value":"26LVMWNI","created_at":"2026-07-05T05:47:15.545669+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/26LVMWNIBFTQE5RT4DZOXWDSFI","json":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI.json","graph_json":"https://pith.science/api/pith-number/26LVMWNIBFTQE5RT4DZOXWDSFI/graph.json","events_json":"https://pith.science/api/pith-number/26LVMWNIBFTQE5RT4DZOXWDSFI/events.json","paper":"https://pith.science/paper/26LVMWNI"},"agent_actions":{"view_html":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI","download_json":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI.json","view_paper":"https://pith.science/paper/26LVMWNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12523&json=true","fetch_graph":"https://pith.science/api/pith-number/26LVMWNIBFTQE5RT4DZOXWDSFI/graph.json","fetch_events":"https://pith.science/api/pith-number/26LVMWNIBFTQE5RT4DZOXWDSFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI/action/storage_attestation","attest_author":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI/action/author_attestation","sign_citation":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI/action/citation_signature","submit_replication":"https://pith.science/pith/26LVMWNIBFTQE5RT4DZOXWDSFI/action/replication_record"}},"created_at":"2026-07-05T05:47:15.545669+00:00","updated_at":"2026-07-05T05:47:15.545669+00:00"}