{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SALAPXFMTGTGFG4TIBRSZ6WZOQ","short_pith_number":"pith:SALAPXFM","schema_version":"1.0","canonical_sha256":"901607dcac99a6629b9340632cfad9743c79a3653eb49e85e3d2df3f53a838bb","source":{"kind":"arxiv","id":"2110.08250","version":2},"attestation_state":"computed","paper":{"title":"Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Danni Liu, Hongyu Gong, Juan Pino, Peng-Jen Chen, Phillip Koehn, Wei-Ning Hsu, Xutai Ma, Yun Tang","submitted_at":"2021-10-15T17:59:15Z","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"},"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":"2110.08250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T17:59:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f0c851cbda83e24be3cbdf30aef084ed7fc84f06db1f9d4e7c40f89bda3643e7","abstract_canon_sha256":"9091816ae329d4a82ee621f0845a8918005cfbaf28ccb4884783f6ec9a5578ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:08.627620Z","signature_b64":"viumJss5EkJUvsd0PcjjwGyAQ4wIoZB2bamuT7wHKANCL/RkWXe/uKj9bPuDoixrbQ4j9zerZlpRNnCzkVH4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901607dcac99a6629b9340632cfad9743c79a3653eb49e85e3d2df3f53a838bb","last_reissued_at":"2026-07-05T03:48:08.627124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:08.627124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Danni Liu, Hongyu Gong, Juan Pino, Peng-Jen Chen, Phillip Koehn, Wei-Ning Hsu, Xutai Ma, Yun Tang","submitted_at":"2021-10-15T17:59:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08250","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/2110.08250/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":"2110.08250","created_at":"2026-07-05T03:48:08.627181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08250v2","created_at":"2026-07-05T03:48:08.627181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08250","created_at":"2026-07-05T03:48:08.627181+00:00"},{"alias_kind":"pith_short_12","alias_value":"SALAPXFMTGTG","created_at":"2026-07-05T03:48:08.627181+00:00"},{"alias_kind":"pith_short_16","alias_value":"SALAPXFMTGTGFG4T","created_at":"2026-07-05T03:48:08.627181+00:00"},{"alias_kind":"pith_short_8","alias_value":"SALAPXFM","created_at":"2026-07-05T03:48:08.627181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.12925","citing_title":"AudioPaLM: A Large Language Model That Can Speak and Listen","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ","json":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ.json","graph_json":"https://pith.science/api/pith-number/SALAPXFMTGTGFG4TIBRSZ6WZOQ/graph.json","events_json":"https://pith.science/api/pith-number/SALAPXFMTGTGFG4TIBRSZ6WZOQ/events.json","paper":"https://pith.science/paper/SALAPXFM"},"agent_actions":{"view_html":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ","download_json":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ.json","view_paper":"https://pith.science/paper/SALAPXFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08250&json=true","fetch_graph":"https://pith.science/api/pith-number/SALAPXFMTGTGFG4TIBRSZ6WZOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SALAPXFMTGTGFG4TIBRSZ6WZOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ/action/storage_attestation","attest_author":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ/action/author_attestation","sign_citation":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ/action/citation_signature","submit_replication":"https://pith.science/pith/SALAPXFMTGTGFG4TIBRSZ6WZOQ/action/replication_record"}},"created_at":"2026-07-05T03:48:08.627181+00:00","updated_at":"2026-07-05T03:48:08.627181+00:00"}