{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SALAPXFMTGTGFG4TIBRSZ6WZOQ","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":"9091816ae329d4a82ee621f0845a8918005cfbaf28ccb4884783f6ec9a5578ad","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T17:59:15Z","title_canon_sha256":"f0c851cbda83e24be3cbdf30aef084ed7fc84f06db1f9d4e7c40f89bda3643e7"},"schema_version":"1.0","source":{"id":"2110.08250","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08250","created_at":"2026-07-05T03:48:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08250v2","created_at":"2026-07-05T03:48:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08250","created_at":"2026-07-05T03:48:08Z"},{"alias_kind":"pith_short_12","alias_value":"SALAPXFMTGTG","created_at":"2026-07-05T03:48:08Z"},{"alias_kind":"pith_short_16","alias_value":"SALAPXFMTGTGFG4T","created_at":"2026-07-05T03:48:08Z"},{"alias_kind":"pith_short_8","alias_value":"SALAPXFM","created_at":"2026-07-05T03:48:08Z"}],"graph_snapshots":[{"event_id":"sha256:a0f6b45b405727dce41764b6f180fb802715d09b24fb864495187ec41cafdcf9","target":"graph","created_at":"2026-07-05T03:48:08Z","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/2110.08250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a direct simultaneous speech-to-speech translation (Simul-S2ST) model, Furthermore, the generation of translation is independent from intermediate text representations. Our approach leverages recent progress on direct speech-to-speech translation with discrete units, in which a sequence of discrete representations, instead of continuous spectrogram features, learned in an unsupervised manner, are predicted from the model and passed directly to a vocoder for speech synthesis on-the-fly. We also introduce the variational monotonic multihead attention (V-MMA), to handle the challenge o","authors_text":"Ann Lee, Danni Liu, Hongyu Gong, Juan Pino, Peng-Jen Chen, Phillip Koehn, Wei-Ning Hsu, Xutai Ma, Yun Tang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T17:59:15Z","title":"Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08250","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:a1c0403f8571cc77ccd6ed56366e05c09bd1c56f2d2cc43c21fff810a6d00829","target":"record","created_at":"2026-07-05T03:48:08Z","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":"9091816ae329d4a82ee621f0845a8918005cfbaf28ccb4884783f6ec9a5578ad","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T17:59:15Z","title_canon_sha256":"f0c851cbda83e24be3cbdf30aef084ed7fc84f06db1f9d4e7c40f89bda3643e7"},"schema_version":"1.0","source":{"id":"2110.08250","kind":"arxiv","version":2}},"canonical_sha256":"901607dcac99a6629b9340632cfad9743c79a3653eb49e85e3d2df3f53a838bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901607dcac99a6629b9340632cfad9743c79a3653eb49e85e3d2df3f53a838bb","first_computed_at":"2026-07-05T03:48:08.627124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:08.627124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"viumJss5EkJUvsd0PcjjwGyAQ4wIoZB2bamuT7wHKANCL/RkWXe/uKj9bPuDoixrbQ4j9zerZlpRNnCzkVH4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:08.627620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08250","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1c0403f8571cc77ccd6ed56366e05c09bd1c56f2d2cc43c21fff810a6d00829","sha256:a0f6b45b405727dce41764b6f180fb802715d09b24fb864495187ec41cafdcf9"],"state_sha256":"875250da4c7848bcb4e22a22429ba3839b560cd96eec815a1fa86e632a68f92b"}