{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HYD7SA525SIHHBERWNJTEPXY6D","short_pith_number":"pith:HYD7SA52","canonical_record":{"source":{"id":"1904.06037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:15:31Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"7b574e487068e29ce9720ef0f0a7f0c47e89b71ea0aa9f34fab6c4fef6424d0b","abstract_canon_sha256":"836b8d311082c474ede1ca298e81f7f4e107e0dfd8518ab796e63f94ee7a8d6e"},"schema_version":"1.0"},"canonical_sha256":"3e07f903baec90738491b353323ef8f0f6566ac501a9b728e961a960de8d45da","source":{"kind":"arxiv","id":"1904.06037","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06037","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06037v2","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06037","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"HYD7SA525SIH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HYD7SA525SIHHBER","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HYD7SA52","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HYD7SA525SIHHBERWNJTEPXY6D","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:15:31Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"7b574e487068e29ce9720ef0f0a7f0c47e89b71ea0aa9f34fab6c4fef6424d0b","abstract_canon_sha256":"836b8d311082c474ede1ca298e81f7f4e107e0dfd8518ab796e63f94ee7a8d6e"},"schema_version":"1.0"},"canonical_sha256":"3e07f903baec90738491b353323ef8f0f6566ac501a9b728e961a960de8d45da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:15.140391Z","signature_b64":"Q3yC4zXDdwNU/3LDZVWJAPxlQ+LoN2mIcieeuHGGEK9A1NNhGu0ynPbCC4n1Fz4+H48i+2109eU3CEM6/YAtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e07f903baec90738491b353323ef8f0f6566ac501a9b728e961a960de8d45da","last_reissued_at":"2026-05-17T23:42:15.139758Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:15.139758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06037","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4zG0JF19CxdGJvLyH6Q0a2PXxvViMvnG8cXrXVHg8bdWQQaZtQeymfVyCfWVT+NTzXZSQITHsjMyooT9MCfRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:18:09.308282Z"},"content_sha256":"d15a163145b05c2e507f23a7c5a1016fb3e378405c4f3e6a4055d61ecc00d4a7","schema_version":"1.0","event_id":"sha256:d15a163145b05c2e507f23a7c5a1016fb3e378405c4f3e6a4055d61ecc00d4a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HYD7SA525SIHHBERWNJTEPXY6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct speech-to-speech translation with a sequence-to-sequence model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Fadi Biadsy, Melvin Johnson, Ron J. Weiss, Wolfgang Macherey, Ye Jia, Yonghui Wu, Zhifeng Chen","submitted_at":"2019-04-12T05:15:31Z","abstract_excerpt":"We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learning to map speech spectrograms into target spectrograms in another language, corresponding to the translated content (in a different canonical voice). We further demonstrate the ability to synthesize translated speech using the voice of the source speaker. We conduct experiments on two Spanish-to-English speech translation datasets, and find that th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06037","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":""},"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":"2026-05-17T23:42:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TH0Q0sq1UOYG/ft7XbgCAjSPcCzqjtd0WBmR9il/wKNWjaXufWADjWEHcPaegx8e804EzjnMjcgodRWKv96iBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:18:09.308975Z"},"content_sha256":"f24d71049dc7b65975a9ab86ee16d4a3852918aca78c27dc788a091077dcc3cd","schema_version":"1.0","event_id":"sha256:f24d71049dc7b65975a9ab86ee16d4a3852918aca78c27dc788a091077dcc3cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/bundle.json","state_url":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYD7SA525SIHHBERWNJTEPXY6D/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":"2026-05-28T21:18:09Z","links":{"resolver":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D","bundle":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/bundle.json","state":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYD7SA525SIHHBERWNJTEPXY6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HYD7SA525SIHHBERWNJTEPXY6D","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":"836b8d311082c474ede1ca298e81f7f4e107e0dfd8518ab796e63f94ee7a8d6e","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:15:31Z","title_canon_sha256":"7b574e487068e29ce9720ef0f0a7f0c47e89b71ea0aa9f34fab6c4fef6424d0b"},"schema_version":"1.0","source":{"id":"1904.06037","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06037","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06037v2","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06037","created_at":"2026-05-17T23:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"HYD7SA525SIH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HYD7SA525SIHHBER","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HYD7SA52","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:f24d71049dc7b65975a9ab86ee16d4a3852918aca78c27dc788a091077dcc3cd","target":"graph","created_at":"2026-05-17T23:42:15Z","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"},"paper":{"abstract_excerpt":"We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learning to map speech spectrograms into target spectrograms in another language, corresponding to the translated content (in a different canonical voice). We further demonstrate the ability to synthesize translated speech using the voice of the source speaker. We conduct experiments on two Spanish-to-English speech translation datasets, and find that th","authors_text":"Fadi Biadsy, Melvin Johnson, Ron J. Weiss, Wolfgang Macherey, Ye Jia, Yonghui Wu, Zhifeng Chen","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:15:31Z","title":"Direct speech-to-speech translation with a sequence-to-sequence model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06037","kind":"arxiv","version":2},"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:d15a163145b05c2e507f23a7c5a1016fb3e378405c4f3e6a4055d61ecc00d4a7","target":"record","created_at":"2026-05-17T23:42:15Z","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":"836b8d311082c474ede1ca298e81f7f4e107e0dfd8518ab796e63f94ee7a8d6e","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T05:15:31Z","title_canon_sha256":"7b574e487068e29ce9720ef0f0a7f0c47e89b71ea0aa9f34fab6c4fef6424d0b"},"schema_version":"1.0","source":{"id":"1904.06037","kind":"arxiv","version":2}},"canonical_sha256":"3e07f903baec90738491b353323ef8f0f6566ac501a9b728e961a960de8d45da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e07f903baec90738491b353323ef8f0f6566ac501a9b728e961a960de8d45da","first_computed_at":"2026-05-17T23:42:15.139758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:15.139758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q3yC4zXDdwNU/3LDZVWJAPxlQ+LoN2mIcieeuHGGEK9A1NNhGu0ynPbCC4n1Fz4+H48i+2109eU3CEM6/YAtCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:15.140391Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06037","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d15a163145b05c2e507f23a7c5a1016fb3e378405c4f3e6a4055d61ecc00d4a7","sha256:f24d71049dc7b65975a9ab86ee16d4a3852918aca78c27dc788a091077dcc3cd"],"state_sha256":"0de1396563a878222617b1d10a536b4884738e2d3a18cee29c9d10c31644b5f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArPb3u4n4qOLb496S2rvLGBRfQv70gKCHePtdXbjFPrSLHaqsEUOHLPACKmqskMOsYwFCck40KR3qmNiT5FnBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:18:09.312741Z","bundle_sha256":"5f86867f0a33d1cee6ac7cbd7adb951977d7a7aa796f304826a04fdb5939a892"}}