{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H5U7WANXQED4VJAZ6BGR5HS5V5","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":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a"},"schema_version":"1.0","source":{"id":"2410.03298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03298","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03298v1","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03298","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"H5U7WANXQED4","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"H5U7WANXQED4VJAZ","created_at":"2026-07-05T09:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"H5U7WANX","created_at":"2026-07-05T09:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:bebe0e6e9c5bcb2e7614fb09c3e0b4e38606802e8f58fa2009666c7e1b951401","target":"graph","created_at":"2026-07-05T09:15:47Z","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/2410.03298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech translation model that outputs discrete speech tokens in a low-latency streaming fashion. This approach eliminates the need for generating text output first, followed by machine translation (MT) and text-to-speech (TTS) systems. The produced speech tokens can be directly used to generate a speech signal with low latency by utilizing an acoustic language model ","authors_text":"Christian Fuegen, Duc Le, Egor Lakomkin, Jinzheng Zhao, Katerina Zmolikova, Niko Moritz, Ruiming Xie, Yashesh Gaur, Zeeshan Ahmed, Zhiping Xiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03298","kind":"arxiv","version":1},"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:d334fdecd90c4230f5d2ed7e7f3903a209eab8ee2b720af0aa9161567b5103f7","target":"record","created_at":"2026-07-05T09:15:47Z","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":"0b14350d5e648201cd421e4d7b425d257c513ac92c7ec32abcb3645bd6ba7ffe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-04T10:21:15Z","title_canon_sha256":"f6acb4b5c200d05c7cb6d8427a318240bb2e17fab27f43886127a7907a716f4a"},"schema_version":"1.0","source":{"id":"2410.03298","kind":"arxiv","version":1}},"canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f69fb01b78107caa419f04d1e9e5daf557be08fe270738590eee384e02dac8f","first_computed_at":"2026-07-05T09:15:47.353442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:47.353442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUhwdUPb2iiurvQEEqWLChVa0JUEKmMxt/46a8xqdCVZ+wanOqA+jyLRY/nDNbwedC7m6i/cwwVItfmw/BxXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:47.353957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d334fdecd90c4230f5d2ed7e7f3903a209eab8ee2b720af0aa9161567b5103f7","sha256:bebe0e6e9c5bcb2e7614fb09c3e0b4e38606802e8f58fa2009666c7e1b951401"],"state_sha256":"fd58545b75534c6f4e5707a9234087839a9f21b9126a850ba1c9bbf30ec862c6"}