{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HYD7SA525SIHHBERWNJTEPXY6D","short_pith_number":"pith:HYD7SA52","schema_version":"1.0","canonical_sha256":"3e07f903baec90738491b353323ef8f0f6566ac501a9b728e961a960de8d45da","source":{"kind":"arxiv","id":"1904.06037","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.06037","created_at":"2026-05-17T23:42:15.139873+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06037v2","created_at":"2026-05-17T23:42:15.139873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06037","created_at":"2026-05-17T23:42:15.139873+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYD7SA525SIH","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYD7SA525SIHHBER","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYD7SA52","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D","json":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D.json","graph_json":"https://pith.science/api/pith-number/HYD7SA525SIHHBERWNJTEPXY6D/graph.json","events_json":"https://pith.science/api/pith-number/HYD7SA525SIHHBERWNJTEPXY6D/events.json","paper":"https://pith.science/paper/HYD7SA52"},"agent_actions":{"view_html":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D","download_json":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D.json","view_paper":"https://pith.science/paper/HYD7SA52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06037&json=true","fetch_graph":"https://pith.science/api/pith-number/HYD7SA525SIHHBERWNJTEPXY6D/graph.json","fetch_events":"https://pith.science/api/pith-number/HYD7SA525SIHHBERWNJTEPXY6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/action/storage_attestation","attest_author":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/action/author_attestation","sign_citation":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/action/citation_signature","submit_replication":"https://pith.science/pith/HYD7SA525SIHHBERWNJTEPXY6D/action/replication_record"}},"created_at":"2026-05-17T23:42:15.139873+00:00","updated_at":"2026-05-17T23:42:15.139873+00:00"}