{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NEHYHK42W4NL5NOWWXBMYMJMJN","short_pith_number":"pith:NEHYHK42","canonical_record":{"source":{"id":"2204.02967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T17:59:22Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0fed6b442029b50a405203c719369c1c90049af21fa5560512c49bfa01ce3ab3","abstract_canon_sha256":"358ca605d90c462b58df23161a1defe49cb57136169379d34ae999d26a802847"},"schema_version":"1.0"},"canonical_sha256":"690f83ab9ab71abeb5d6b5c2cc312c4b741db1f3aaa9b136e2e7f000864fcefa","source":{"kind":"arxiv","id":"2204.02967","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02967","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02967v3","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02967","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"pith_short_12","alias_value":"NEHYHK42W4NL","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"pith_short_16","alias_value":"NEHYHK42W4NL5NOW","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"pith_short_8","alias_value":"NEHYHK42","created_at":"2026-07-05T04:57:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NEHYHK42W4NL5NOWWXBMYMJMJN","target":"record","payload":{"canonical_record":{"source":{"id":"2204.02967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T17:59:22Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0fed6b442029b50a405203c719369c1c90049af21fa5560512c49bfa01ce3ab3","abstract_canon_sha256":"358ca605d90c462b58df23161a1defe49cb57136169379d34ae999d26a802847"},"schema_version":"1.0"},"canonical_sha256":"690f83ab9ab71abeb5d6b5c2cc312c4b741db1f3aaa9b136e2e7f000864fcefa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:07.088498Z","signature_b64":"Umnt+JrrfJtjASoE6f53pVxtsDIDcJcHJJtM0kJItl+OSuwl24kzZP1RLR04kaSJ2bMh5Yd09jUpBuUDFU+xCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"690f83ab9ab71abeb5d6b5c2cc312c4b741db1f3aaa9b136e2e7f000864fcefa","last_reissued_at":"2026-07-05T04:57:07.087859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:07.087859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.02967","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:57:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3RcyVmd3y8T1qCvHHE+7t5hFbTwnuTvlhq/heXvWXNEYabb0pFOZjeNXqpoHzn+wJHxAxwsqabyCiQY6EgZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:26:35.251545Z"},"content_sha256":"4f5eaedbe8df14d5bc2ce79ee91f53b9a4d299115d221fdf54665da1be23d2ac","schema_version":"1.0","event_id":"sha256:4f5eaedbe8df14d5bc2ce79ee91f53b9a4d299115d221fdf54665da1be23d2ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NEHYHK42W4NL5NOWWXBMYMJMJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Changhan Wang, Jiatao Gu, Juan Pino, Peng-Jen Chen, Sravya Popuri, Wei-Ning Hsu, Yossi Adi","submitted_at":"2022-04-06T17:59:22Z","abstract_excerpt":"Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS) synthesis. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue. We take advantage of a recently proposed speech-to-unit translation (S2UT) framework that encodes target speech into discrete representations, and transfer pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02967","kind":"arxiv","version":3},"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/2204.02967/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:57:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/cXq/Zyx5N2MqiwR5Mrax3RUf3vQ4JkXxf5Cl8Qfpr6pwuW1jye56IXoxIUdRyHIgNPTxMwFw/Cc1BONRXtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:26:35.252467Z"},"content_sha256":"90b6ad0113657a027736dd5be741149d81744e93d869853e02d01d8fc0e3496b","schema_version":"1.0","event_id":"sha256:90b6ad0113657a027736dd5be741149d81744e93d869853e02d01d8fc0e3496b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NEHYHK42W4NL5NOWWXBMYMJMJN/bundle.json","state_url":"https://pith.science/pith/NEHYHK42W4NL5NOWWXBMYMJMJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NEHYHK42W4NL5NOWWXBMYMJMJN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T13:26:35Z","links":{"resolver":"https://pith.science/pith/NEHYHK42W4NL5NOWWXBMYMJMJN","bundle":"https://pith.science/pith/NEHYHK42W4NL5NOWWXBMYMJMJN/bundle.json","state":"https://pith.science/pith/NEHYHK42W4NL5NOWWXBMYMJMJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NEHYHK42W4NL5NOWWXBMYMJMJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NEHYHK42W4NL5NOWWXBMYMJMJN","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":"358ca605d90c462b58df23161a1defe49cb57136169379d34ae999d26a802847","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T17:59:22Z","title_canon_sha256":"0fed6b442029b50a405203c719369c1c90049af21fa5560512c49bfa01ce3ab3"},"schema_version":"1.0","source":{"id":"2204.02967","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02967","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02967v3","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02967","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"pith_short_12","alias_value":"NEHYHK42W4NL","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"pith_short_16","alias_value":"NEHYHK42W4NL5NOW","created_at":"2026-07-05T04:57:07Z"},{"alias_kind":"pith_short_8","alias_value":"NEHYHK42","created_at":"2026-07-05T04:57:07Z"}],"graph_snapshots":[{"event_id":"sha256:90b6ad0113657a027736dd5be741149d81744e93d869853e02d01d8fc0e3496b","target":"graph","created_at":"2026-07-05T04:57:07Z","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/2204.02967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS) synthesis. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue. We take advantage of a recently proposed speech-to-unit translation (S2UT) framework that encodes target speech into discrete representations, and transfer pre-","authors_text":"Ann Lee, Changhan Wang, Jiatao Gu, Juan Pino, Peng-Jen Chen, Sravya Popuri, Wei-Ning Hsu, Yossi Adi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T17:59:22Z","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02967","kind":"arxiv","version":3},"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":"sha256:4f5eaedbe8df14d5bc2ce79ee91f53b9a4d299115d221fdf54665da1be23d2ac","target":"record","created_at":"2026-07-05T04:57:07Z","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":"358ca605d90c462b58df23161a1defe49cb57136169379d34ae999d26a802847","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T17:59:22Z","title_canon_sha256":"0fed6b442029b50a405203c719369c1c90049af21fa5560512c49bfa01ce3ab3"},"schema_version":"1.0","source":{"id":"2204.02967","kind":"arxiv","version":3}},"canonical_sha256":"690f83ab9ab71abeb5d6b5c2cc312c4b741db1f3aaa9b136e2e7f000864fcefa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"690f83ab9ab71abeb5d6b5c2cc312c4b741db1f3aaa9b136e2e7f000864fcefa","first_computed_at":"2026-07-05T04:57:07.087859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:07.087859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Umnt+JrrfJtjASoE6f53pVxtsDIDcJcHJJtM0kJItl+OSuwl24kzZP1RLR04kaSJ2bMh5Yd09jUpBuUDFU+xCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:07.088498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02967","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f5eaedbe8df14d5bc2ce79ee91f53b9a4d299115d221fdf54665da1be23d2ac","sha256:90b6ad0113657a027736dd5be741149d81744e93d869853e02d01d8fc0e3496b"],"state_sha256":"2dcf27731bf86d875b1204f1413ac68bb75bfd923ca78a67d99d4cb9d2003184"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIn/zwaMLNd8Fh6VXOLQOXiASieGKSKVQPwVB6C6wGSNdS2rhBtmodZLW7aG9DIQe289Om0YhXP1f37kNFnICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:26:35.262674Z","bundle_sha256":"b9c7865a1da221e92014c0a83f5f1e2b5348e200bd42f4470a7bbca8b6af9c26"}}